메뉴 건너뛰기




Volumn 9780521841085, Issue , 2006, Pages 1-394

Prediction, learning, and games

Author keywords

[No Author keywords available]

Indexed keywords

EDUCATION; INVESTMENTS;

EID: 84926078662     PISSN: None     EISSN: None     Source Type: Book    
DOI: 10.1017/CBO9780511546921     Document Type: Book
Times cited : (3968)

References (320)
  • 1
    • 33747454027 scopus 로고
    • The method of potential functions for the problem of restoring the characteristic of a function converter from randomly observed points
    • M.A. Aizerman, E.M. Braverman, and L.I. Rozonoer. The method of potential functions for the problem of restoring the characteristic of a function converter from randomly observed points. Automation and Remote Control, 25:1546-1556, 1964.
    • (1964) Automation and Remote Control , vol.25 , pp. 1546-1556
    • Aizerman, M.A.1    Braverman, E.M.2    Rozonoer, L.I.3
  • 2
    • 33747467331 scopus 로고
    • The probability problem of pattern recognition learning and the method of potential functions
    • M.A. Aizerman, E.M. Braverman, and L.I. Rozonoer. The probability problem of pattern recognition learning and the method of potential functions. Automation and Remote Control, 25:1307-1323, 1964.
    • (1964) Automation and Remote Control , vol.25 , pp. 1307-1323
    • Aizerman, M.A.1    Braverman, E.M.2    Rozonoer, L.I.3
  • 3
    • 84932021208 scopus 로고
    • Theoretical foundations of the potential function method in pattern recognition learning
    • M.A. Aizerman, E.M. Braverman, and L.I. Rozonoer. Theoretical foundations of the potential function method in pattern recognition learning. Automation and Remote Control, 25:917-936, 1964.
    • (1964) Automation and Remote Control , vol.25 , pp. 917-936
    • Aizerman, M.A.1    Braverman, E.M.2    Rozonoer, L.I.3
  • 4
    • 0000551326 scopus 로고
    • Universal schemes for prediction, gambling, and portfolio selection
    • P. Algoet. Universal schemes for prediction, gambling, and portfolio selection. Annals of Probability, 20:901-941, 1992.
    • (1992) Annals of Probability , vol.20 , pp. 901-941
    • Algoet, P.1
  • 5
    • 0028428283 scopus 로고
    • The strong law of large numbers for sequential decisions under uncertainty
    • P. Algoet. The strong law of large numbers for sequential decisions under uncertainty. IEEE Transactions on Information Theory, 40:609-634, 1994.
    • (1994) IEEE Transactions on Information Theory , vol.40 , pp. 609-634
    • Algoet, P.1
  • 6
    • 0000801141 scopus 로고
    • Asymptotic optimality and asymptotic equipartition properties of log-optimum investment
    • P. Algoet and T. Cover. Asymptotic optimality and asymptotic equipartition properties of log-optimum investment. Annals of Probability, 16(2):876-898, 1988.
    • (1988) Annals of Probability , vol.16 , Issue.2 , pp. 876-898
    • Algoet, P.1    Cover, T.2
  • 8
    • 0000759079 scopus 로고
    • The adatron: An adaptive Perceptron algorithm
    • J.K. Anlauf and M. Biehl. The Adatron: An adaptive Perceptron algorithm. Europhysics Letters, 10:687-692, 1989.
    • (1989) Europhysics Letters , vol.10 , pp. 687-692
    • Anlauf, J.K.1    Biehl, M.2
  • 10
    • 0041966002 scopus 로고    scopus 로고
    • Using confidence bounds for exploitation-exploration trade-offs
    • P. Auer. Using confidence bounds for exploitation-exploration trade-offs. Journal of Machine Learning Research, 3:397-422, 2002.
    • (2002) Journal of Machine Learning Research , vol.3 , pp. 397-422
    • Auer, P.1
  • 11
    • 0036568025 scopus 로고    scopus 로고
    • Finite-time analysis of the multiarmed bandit problem
    • P. Auer, N. Cesa-Bianchi, and P. Fischer. Finite-time analysis of the multiarmed bandit problem. Machine Learning, 47:235-256, 2002.
    • (2002) Machine Learning , vol.47 , pp. 235-256
    • Auer, P.1    Cesa-Bianchi, N.2    Fischer, P.3
  • 14
    • 0032595785 scopus 로고    scopus 로고
    • Structural results for online learning models with and without queries
    • P. Auer and P.M. Long. Structural results for online learning models with and without queries. Machine Learning, 36(3):147-181, 1999.
    • (1999) Machine Learning , vol.36 , Issue.3 , pp. 147-181
    • Auer, P.1    Long, P.M.2
  • 15
    • 0032140937 scopus 로고    scopus 로고
    • Tracking the best disjunction
    • P. Auer and M. Warmuth. Tracking the best disjunction. Machine Learning, 32(2):127-150, 1998.
    • (1998) Machine Learning , vol.32 , Issue.2 , pp. 127-150
    • Auer, P.1    Warmuth, M.2
  • 16
    • 0002430114 scopus 로고
    • Subjectivity and correlation in randomized strategies
    • R.J. Aumann. Subjectivity and correlation in randomized strategies. Journal of Mathematical Economics, 1:67-96, 1974.
    • (1974) Journal of Mathematical Economics , vol.1 , pp. 67-96
    • Aumann, R.J.1
  • 17
    • 0002220788 scopus 로고
    • Correlated equilibrium as an expression of Bayesian rationality
    • R.J. Aumann. Correlated equilibrium as an expression of Bayesian rationality. Econometrica,55:1-18, 1987.
    • (1987) Econometrica , vol.55 , pp. 1-18
    • Aumann, R.J.1
  • 19
    • 4544345025 scopus 로고    scopus 로고
    • Adaptive routing with end-to-end feedback: Distributed learning and geometric approaches
    • ACM Press, New York
    • B. Awerbuch and R.D. Kleinberg. Adaptive routing with end-to-end feedback: Distributed learning and geometric approaches. In Proceedings of the 36th ACM Symposium on the Theory of Computing, pp. 45-53. ACM Press, New York, 2004.
    • (2004) Proceedings of the 36th ACM Symposium on the Theory of Computing , pp. 45-53
    • Awerbuch, B.1    Kleinberg, R.D.2
  • 20
    • 0035370926 scopus 로고    scopus 로고
    • Relative loss bounds for on-line density estimation with the exponential family of distributions
    • K.S. Azoury and M. Warmuth. Relative loss bounds for on-line density estimation with the exponential family of distributions. Machine Learning, 43(3):211-246, 2001.
    • (2001) Machine Learning , vol.43 , Issue.3 , pp. 211-246
    • Azoury, K.S.1    Warmuth, M.2
  • 22
  • 23
    • 0039607373 scopus 로고
    • Potential function algorithms for pattern recognition learning machines
    • O. Bashkirov, E.M. Braverman, and I.E. Muchnik. Potential function algorithms for pattern recognition learning machines. Automation and Remote Control, 25:692-695, 1964.
    • (1964) Automation and Remote Control , vol.25 , pp. 692-695
    • Bashkirov, O.1    Braverman, E.M.2    Muchnik, I.E.3
  • 24
    • 0037403111 scopus 로고    scopus 로고
    • Mirror descent and nonlinear projected subgradient methods for convex optimization
    • A. Beck and M. Teboulle. Mirror descent and nonlinear projected subgradient methods for convex optimization. Operations Research Letters, 31:167-175, 2003.
    • (2003) Operations Research Letters , vol.31 , pp. 167-175
    • Beck, A.1    Teboulle, M.2
  • 28
    • 84972545864 scopus 로고
    • An analog of the minimax theorem for vector payoffs
    • D. Blackwell. An analog of the minimax theorem for vector payoffs. Pacific Journal of Mathematics, 6:1-8, 1956.
    • (1956) Pacific Journal of Mathematics , vol.6 , pp. 1-8
    • Blackwell, D.1
  • 31
    • 0000430986 scopus 로고
    • The Perceptron: A model for brain functioning
    • H.D. Block. The Perceptron: A model for brain functioning. Review of Modern Physics, 34:123-135, 1962.
    • (1962) Review of Modern Physics , vol.34 , pp. 123-135
    • Block, H.D.1
  • 32
    • 0033904366 scopus 로고    scopus 로고
    • On-line learning and the metrical task system problem
    • A. Blum and C. Burch. On-line learning and the metrical task system problem. Machine Learning, 39:35-58, 2000.
    • (2000) Machine Learning , vol.39 , pp. 35-58
    • Blum, A.1    Burch, C.2
  • 33
    • 0032686447 scopus 로고    scopus 로고
    • Universal portfolios with and without transaction costs
    • A. Blum and A. Kalai. Universal portfolios with and without transaction costs. Machine Learning, 35:193-205, 1999.
    • (1999) Machine Learning , vol.35 , pp. 193-205
    • Blum, A.1    Kalai, A.2
  • 35
    • 25444522689 scopus 로고    scopus 로고
    • Fast kernel classifiers with online and active learning
    • Microtome Publishing, Brookline, MA
    • A. Bordes, S. Ertekin, J. Weston, and L. Bottou. Fast kernel classifiers with online and active learning. Journal of Machine Learning Research, 6:1579-1619. Microtome Publishing, Brookline, MA, 2005.
    • (2005) Journal of Machine Learning Research , vol.6 , pp. 1579-1619
    • Bordes, A.1    Ertekin, S.2    Weston, J.3    Bottou, L.4
  • 39
    • 17444399859 scopus 로고    scopus 로고
    • Stochastic approximations and efficient learning
    • M.A. Arbib, Cambridge University Press, New York
    • L. Bottou and N. Murata. Stochastic approximations and efficient learning. In M.A. Arbib, ed., The Handbook of Brain Theory and Neural Networks. Cambridge University Press, New York, 2002. 2nd edition.
    • (2002) The Handbook of Brain Theory and Neural Networks
    • Bottou, L.1    Murata, N.2
  • 40
    • 0041965987 scopus 로고    scopus 로고
    • Tracking a small set of experts by mixing past posteriors
    • O. Bousquet and M. Warmuth. Tracking a small set of experts by mixing past posteriors. Journal of Machine Learning Research, 3:363-396, 2002.
    • (2002) Journal of Machine Learning Research , vol.3 , pp. 363-396
    • Bousquet, O.1    Warmuth, M.2
  • 42
    • 0003010182 scopus 로고
    • Verification of forecasts expressed in terms of probability
    • G.W. Brier. Verification of forecasts expressed in terms of probability. Monthly Weather Review, 75:1-3, 1950.
    • (1950) Monthly Weather Review , vol.75 , pp. 1-3
    • Brier, G.W.1
  • 44
    • 12144260119 scopus 로고    scopus 로고
    • General procedures leading to correlated equilibria
    • A. Cahn. General procedures leading to correlated equilibria. International Journal of Game Theory, 33(1):21-40, 2004.
    • (2004) International Journal of Game Theory , vol.33 , Issue.1 , pp. 21-40
    • Cahn, A.1
  • 46
    • 0033285751 scopus 로고    scopus 로고
    • Analysis of two gradient-based algorithms for on-line regression
    • N. Cesa-Bianchi. Analysis of two gradient-based algorithms for on-line regression. Journal of Computer and System Sciences, 59(3):392-411, 1999.
    • (1999) Journal of Computer and System Sciences , vol.59 , Issue.3 , pp. 392-411
    • Cesa-Bianchi, N.1
  • 49
    • 25444456131 scopus 로고    scopus 로고
    • Worst-case analysis of selective sampling for linear-threshold algorithms
    • MIT Press, Cambridge, MA
    • N. Cesa-Bianchi, C. Gentile, and L. Zaniboni. Worst-case analysis of selective sampling for linear-threshold algorithms. In Advances in Neural Information Processing Systems 17, pp. 241-248. MIT Press, Cambridge, MA, 2005.
    • (2005) Advances in Neural Information Processing Systems , vol.17 , pp. 241-248
    • Cesa-Bianchi, N.1    Gentile, C.2    Zaniboni, L.3
  • 50
    • 0030145382 scopus 로고    scopus 로고
    • Worst-case quadratic loss bounds for prediction using linear functions and gradient descent
    • N. Cesa-Bianchi, P.M. Long, and M. Warmuth. Worst-case quadratic loss bounds for prediction using linear functions and gradient descent. IEEE Transactions on Neural Networks, 7(3):604-619, 1996.
    • (1996) IEEE Transactions on Neural Networks , vol.7 , Issue.3 , pp. 604-619
    • Cesa-Bianchi, N.1    Long, P.M.2    Warmuth, M.3
  • 51
    • 0033234631 scopus 로고    scopus 로고
    • On prediction of individual sequences
    • N. Cesa-Bianchi and G. Lugosi. On prediction of individual sequences. Annals of Statistics,27:1865-1895, 1999.
    • (1999) Annals of Statistics , vol.27 , pp. 1865-1895
    • Cesa-Bianchi, N.1    Lugosi, G.2
  • 53
    • 0035371298 scopus 로고    scopus 로고
    • Worst-case bounds for the logarithmic loss of predictors
    • N. Cesa-Bianchi and G. Lugosi. Worst-case bounds for the logarithmic loss of predictors. Machine Learning, 43:247-264, 2001.
    • (2001) Machine Learning , vol.43 , pp. 247-264
    • Cesa-Bianchi, N.1    Lugosi, G.2
  • 54
    • 0037614825 scopus 로고    scopus 로고
    • Potential-based algorithms in on-line prediction and game theory
    • N. Cesa-Bianchi and G. Lugosi. Potential-based algorithms in on-line prediction and game theory. Machine Learning, 51:239-261, 2003.
    • (2003) Machine Learning , vol.51 , pp. 239-261
    • Cesa-Bianchi, N.1    Lugosi, G.2
  • 58
    • 0030544315 scopus 로고    scopus 로고
    • Laws of large numbers for Hilbert space-valued mixingales with applications
    • X. Chen and H. White. Laws of large numbers for Hilbert space-valued mixingales with applications. Econometric Theory, 12(2):284-304, 1996.
    • (1996) Econometric Theory , vol.12 , Issue.2 , pp. 284-304
    • Chen, X.1    White, H.2
  • 63
    • 0002138061 scopus 로고
    • Jeffrys' prior is asymptotically least favorable under entropy risk
    • B. Clarke and A. Barron. Jeffrys' prior is asymptotically least favorable under entropy risk. Journal of Statistical Planning and Inference, 41:37-60, 1994.
    • (1994) Journal of Statistical Planning and Inference , vol.41 , pp. 37-60
    • Clarke, B.1    Barron, A.2
  • 65
    • 0001345686 scopus 로고    scopus 로고
    • Context-sensitive learning methods for text categorization
    • W. Cohen and Y. Singer. Context-sensitive learning methods for text categorization. ACM Transactions on Information Systems, 17:141-173, 1999.
    • (1999) ACM Transactions on Information Systems , vol.17 , pp. 141-173
    • Cohen, W.1    Singer, Y.2
  • 66
    • 0003283879 scopus 로고
    • Training connectionist networks with queries and selective sampling
    • MIT Press, Cambridge, MA
    • R. Cohn, L. Atlas, and R. Ladner. Training connectionist networks with queries and selective sampling. In Advances in Neural Information Processing Systems 2, pp. 566-573. MIT Press, Cambridge, MA, 1990.
    • (1990) Advances in Neural Information Processing Systems , vol.2 , pp. 566-573
    • Cohn, R.1    Atlas, L.2    Ladner, R.3
  • 70
    • 84986753988 scopus 로고
    • Universal portfolios
    • T. Cover. Universal portfolios. Mathematical Finance, 1:1-29, 1991.
    • (1991) Mathematical Finance , vol.1 , pp. 1-29
    • Cover, T.1
  • 75
    • 0141496132 scopus 로고    scopus 로고
    • Ultraconservative online algorithms for multiclass problems
    • K. Crammer and Y. Singer. Ultraconservative online algorithms for multiclass problems. Journal of Machine Learning Research, 3:951-991, 2003.
    • (2003) Journal of Machine Learning Research , vol.3 , pp. 951-991
    • Crammer, K.1    Singer, Y.2
  • 78
    • 0141971259 scopus 로고    scopus 로고
    • Efficient universal portfolios for past-dependent target classes
    • J.E. Cross and A. Barron. Efficient universal portfolios for past-dependent target classes. Mathematical Finance, 13:245-276, 2003.
    • (2003) Mathematical Finance , vol.13 , pp. 245-276
    • Cross, J.E.1    Barron, A.2
  • 82
    • 0001740042 scopus 로고
    • Calibration-based empirical probability
    • A. Dawid. Calibration-based empirical probability. The Annals of Statistics, 13:1251-1285, 1985.
    • (1985) The Annals of Statistics , vol.13 , pp. 1251-1285
    • Dawid, A.1
  • 84
    • 0038225344 scopus 로고
    • Prequential data analysis
    • IMS Lecture Notes - Monograph Series
    • A. Dawid. Prequential data analysis. Current Issues in Statistical Inference, IMS Lecture Notes - Monograph Series 17, pp. 113-126, 1992.
    • (1992) Current Issues in Statistical Inference , vol.17 , pp. 113-126
    • Dawid, A.1
  • 85
    • 33845304828 scopus 로고    scopus 로고
    • How to combine expert (or novice) advice when actions impact the environment
    • MIT Press, Cambridge, MA
    • D.P. de Farias and N. Megiddo. How to combine expert (or novice) advice when actions impact the environment. In Advances in Neural Information Processing Systems 16. MIT Press, Cambridge, MA, 2004.
    • Advances in Neural Information Processing Systems , vol.16 , pp. 2004
    • De Farias, D.P.1    Megiddo, N.2
  • 86
    • 33646519163 scopus 로고    scopus 로고
    • Combining expert advice in reactive environments
    • MIT Press, Cambridge, MA
    • D.P. de Farias and N. Megiddo. Combining expert advice in reactive environments. In Advances in Neural Information Processing Systems, vol. 17, pp. 409-416. MIT Press, Cambridge, MA, 2005.
    • (2005) Advances in Neural Information Processing Systems , vol.17 , pp. 409-416
    • De Farias, D.P.1    Megiddo, N.2
  • 89
    • 0029342607 scopus 로고
    • Lower bounds in pattern recognition and learning
    • L. Devroye and G. Lugosi. Lower bounds in pattern recognition and learning. Pattern Recognition, 28:1011-1018, 1995.
    • (1995) Pattern Recognition , vol.28 , pp. 1011-1018
    • Devroye, L.1    Lugosi, G.2
  • 91
    • 0000421687 scopus 로고
    • Central limit theorems for empirical measures
    • R.M. Dudley. Central limit theorems for empirical measures. Annals of Probability, 6:899-929, 1978.
    • (1978) Annals of Probability , vol.6 , pp. 899-929
    • Dudley, R.M.1
  • 92
    • 0031527291 scopus 로고    scopus 로고
    • On Blackwell's minimax theorem and the compound decision method
    • V. Fabian and J. Hannan. On Blackwell's minimax theorem and the compound decision method. Statistica Sinica, 7:195-209, 1997.
    • (1997) Statistica Sinica , vol.7 , pp. 195-209
    • Fabian, V.1    Hannan, J.2
  • 97
    • 0001783943 scopus 로고
    • Regularité des trajectoires des fonctions a1éatoires gaussiennes
    • École d'Été de Probabilités de Saint-Flour, IV-1974, Springer, New York
    • X. Fernique. Regularité des trajectoires des fonctions a1éatoires gaussiennes. In École d'Été de Probabilités de Saint-Flour, IV-1974, vol. 480 of Lecture Notes in Math, pp. 1-96. Springer, New York, 1975.
    • (1975) Ecole d’Eté De Probabilités De Saint-Flour, IV-1974 , vol.480 , pp. 1-96
    • Fernique, X.1
  • 98
    • 0001783943 scopus 로고
    • Regularité de fonctions aléatoires non gaussiennes
    • Springer, New York
    • X. Fernique. Regularité de fonctions aléatoires non gaussiennes. In École d'Été de Probabilités deSaint-Flour, XI-1981, volume 976 of LectureNotes inMath., pp. 1-74. Springer, New York, 1983.
    • (1983) École d'Été de Probabilités deSaint-Flour, XI-1981 , vol.976 , pp. 1-74
    • Fernique, X.1
  • 99
    • 33746354147 scopus 로고
    • Optimal coding for unknown and variable statistics of messages
    • B.M. Fitingof. Optimal coding for unknown and variable statistics of messages. Problems of Information Transmission, 2:3-11, 1966.
    • (1966) Problems of Information Transmission , vol.2 , pp. 3-11
    • Fitingof, B.M.1
  • 101
    • 0011593185 scopus 로고
    • Correlated equilibrium in two-person zero-sum games
    • F. Forges. Correlated equilibrium in two-person zero-sum games. Econometrica, 58:515, 1990.
    • (1990) Econometrica , vol.58 , pp. 515
    • Forges, F.1
  • 102
    • 84956865170 scopus 로고    scopus 로고
    • On relative loss bounds in generalized linear regression
    • Lecture Notes in Computer Science 1684, Springer-Verlag, Berlin
    • J. Forster. On relative loss bounds in generalized linear regression. In Proceedings of the 12th International Symposium on Fundamentals of Computation Theory, pp. 269-280. Lecture Notes in Computer Science 1684, Springer-Verlag, Berlin, 1999.
    • (1999) Proceedings of the 12th International Symposium on Fundamentals of Computation Theory , pp. 269-280
    • Forster, J.1
  • 103
    • 0000349751 scopus 로고
    • Prediction in the worst-case
    • D. Foster. Prediction in the worst-case. Annals of Statistics, 19:1084-1090, 1991.
    • (1991) Annals of Statistics , vol.19 , pp. 1084-1090
    • Foster, D.1
  • 104
    • 0042186389 scopus 로고    scopus 로고
    • A proof of calibration via Blackwell's approachability theorem
    • D. Foster. A proof of calibration via Blackwell's approachability theorem. Games and Economic Behavior, 29:73-78, 1999.
    • (1999) Games and Economic Behavior , vol.29 , pp. 73-78
    • Foster, D.1
  • 105
    • 0031256578 scopus 로고    scopus 로고
    • Calibrated learning and correlated equilibrium
    • D. Foster and R. Vohra. Calibrated learning and correlated equilibrium. Games and Economic Behaviour, 21:40-55, 1997.
    • (1997) Games and Economic Behaviour , vol.21 , pp. 40-55
    • Foster, D.1    Vohra, R.2
  • 106
    • 0037539108 scopus 로고    scopus 로고
    • Asymptotic calibration
    • D. Foster and R. Vohra. Asymptotic calibration. Biometrika, 85:379-390, 1998.
    • (1998) Biometrika , vol.85 , pp. 379-390
    • Foster, D.1    Vohra, R.2
  • 107
  • 108
    • 0141838158 scopus 로고    scopus 로고
    • Learning, hypothesis testing, and Nash equilibrium
    • D. Foster and P.H. Young. Learning, hypothesis testing, and Nash equilibrium. Games and Economic Behavior, 45:73-96, 2003.
    • (2003) Games and Economic Behavior , vol.45 , pp. 73-96
    • Foster, D.1    Young, P.H.2
  • 110
    • 0002384441 scopus 로고
    • On tail probabilities for martingales
    • D.A. Freedman. On tail probabilities for martingales. Annals of Probability, 3:100-118, 1975.
    • (1975) Annals of Probability , vol.3 , pp. 100-118
    • Freedman, D.A.1
  • 112
    • 0031211090 scopus 로고    scopus 로고
    • A decision-theoretic generalization of on-line learning and an application to boosting
    • Y. Freund and R. Schapire. A decision-theoretic generalization of on-line learning and an application to boosting. Journal of Computer and System Sciences, 55:119-139, 1997.
    • (1997) Journal of Computer and System Sciences , vol.55 , pp. 119-139
    • Freund, Y.1    Schapire, R.2
  • 113
    • 0002267135 scopus 로고    scopus 로고
    • Adaptive game playing using multiplicative weights
    • Y. Freund and R. Schapire. Adaptive game playing using multiplicative weights. Games and Economic Behavior, 29:79-103, 1999.
    • (1999) Games and Economic Behavior , vol.29 , pp. 79-103
    • Freund, Y.1    Schapire, R.2
  • 114
    • 0033281425 scopus 로고    scopus 로고
    • Large margin classification using the Perceptron algorithm
    • Y. Freund and R. Schapire. Large margin classification using the Perceptron algorithm. Machine Learning, 37(3): 277-296, 1999.
    • (1999) Machine Learning , vol.37 , Issue.3 , pp. 277-296
    • Freund, Y.1    Schapire, R.2
  • 116
    • 0031209604 scopus 로고    scopus 로고
    • Selective sampling using the query by committee algorithm
    • Y. Freund, S. Seung, E. Shamir, and N. Tishby. Selective sampling using the query by committee algorithm. Machine Learning, 28(2/3):133-168, 1997.
    • (1997) Machine Learning , vol.28 , Issue.2-3 , pp. 133-168
    • Freund, Y.1    Seung, S.2    Shamir, E.3    Tishby, N.4
  • 117
    • 0001288755 scopus 로고
    • Steady state learning and Nash equilibrium
    • D. Fudenberg and D.K. Levine. Steady state learning and Nash equilibrium. Econometrica, 61:547-573, 1993.
    • (1993) Econometrica , vol.61 , pp. 547-573
    • Fudenberg, D.1    Levine, D.K.2
  • 123
    • 84868111801 scopus 로고    scopus 로고
    • A new approximate maximal margin classification algorithm
    • C. Gentile. A new approximate maximal margin classification algorithm. Journal of Machine Learning Research, 2:213-242, 2001.
    • (2001) Journal of Machine Learning Research , vol.2 , pp. 213-242
    • Gentile, C.1
  • 124
    • 0344875562 scopus 로고    scopus 로고
    • The robustness of the p-norm algorithms
    • C. Gentile. The robustness of the p-norm algorithms. Machine Learning, 53(3):265-299, 2003.
    • (2003) Machine Learning , vol.53 , Issue.3 , pp. 265-299
    • Gentile, C.1
  • 129
    • 84891584370 scopus 로고
    • Wiley-Interscience series in Systems and Optimization
    • Wiley, New York
    • J.C. Gittins. Multi-Armed Bandit Allocation Indices. Wiley-Interscience series in Systems and Optimization. Wiley, New York, 1989.
    • (1989) Multi-Armed Bandit Allocation Indices
    • Gittins, J.C.1
  • 130
    • 49949150022 scopus 로고
    • Language identification in the limit
    • E.M. Gold. Language identification in the limit. Information and Control, 10:447-474, 1967.
    • (1967) Information and Control , vol.10 , pp. 447-474
    • Gold, E.M.1
  • 133
    • 0035370643 scopus 로고    scopus 로고
    • General convergence results for linear discriminant updates
    • A.J. Grove, N. Littlestone, and D. Schuurmans. General convergence results for linear discriminant updates. Machine Learning, 43(3):173-210, 2001.
    • (2001) Machine Learning , vol.43 , Issue.3 , pp. 173-210
    • Grove, A.J.1    Littlestone, N.2    Schuurmans, D.3
  • 134
    • 33749560322 scopus 로고    scopus 로고
    • A tutorial introduction to the minimum description length principle
    • P. Grünwald, I.J. Myung, and M. Pitt, MIT Press, Cambridge, MA
    • P. Grünwald. A tutorial introduction to the minimum description length principle. In P. Grünwald, I.J. Myung, and M. Pitt, eds., Advances in Minimum Description Length: Theory and Applications. MIT Press, Cambridge, MA, 2005.
    • (2005) Advances in Minimum Description Length: Theory and Applications
    • Grünwald, P.1
  • 135
    • 49449105007 scopus 로고    scopus 로고
    • Nonparametric kernel-based sequential investment strategies
    • Press
    • L. Györfi, G. Lugosi, and F. Udina. Nonparametric kernel-based sequential investment strategies. Mathematical Finance, 2005. In Press.
    • (2005) Mathematical Finance
    • Györfi, L.1    Lugosi, G.2    Udina, F.3
  • 137
    • 3543091481 scopus 로고    scopus 로고
    • Efficient algorithms and minimax bounds for zero-delay lossy source coding
    • A. György, T. Linder, and G. Lugosi. Efficient algorithms and minimax bounds for zero-delay lossy source coding. IEEE Transactions on Signal Processing, 52:2337-2347, 2004.
    • (2004) IEEE Transactions on Signal Processing , vol.52 , pp. 2337-2347
    • György, A.1    Linder, T.2    Lugosi, G.3
  • 138
    • 2642551766 scopus 로고    scopus 로고
    • A “follow the perturbed leader”-type algorithm for zerodelay quantization of individual sequences
    • IEEE Computer Society Press, Los Alamitos, CA
    • A. György, T. Linder, and G. Lugosi. A “follow the perturbed leader”-type algorithm for zerodelay quantization of individual sequences. In Data Compression Conference, pp. 342-351. IEEE Computer Society Press, Los Alamitos, CA, 2004.
    • (2004) Data Compression Conference , pp. 342-351
    • György, A.1    Linder, T.2    Lugosi, G.3
  • 141
    • 0001976283 scopus 로고
    • Approximation to Bayes risk in repeated play
    • J. Hannan. Approximation to Bayes risk in repeated play. Contributions to the Theory of Games, 3:97-139, 1957.
    • (1957) Contributions to the Theory of Games , vol.3 , pp. 97-139
    • Hannan, J.1
  • 142
    • 0003179923 scopus 로고
    • Asymptotic solutions of the compound decision problem for two completely specified distributions
    • J. Hannan and H. Robbins. Asymptotic solutions of the compound decision problem for two completely specified distributions. Annals of Mathematical Statistics, 26:37-51, 1955.
    • (1955) Annals of Mathematical Statistics , vol.26 , pp. 37-51
    • Hannan, J.1    Robbins, H.2
  • 143
  • 144
    • 16244398351 scopus 로고    scopus 로고
    • Technical Report DP-372, Center for Rationality, The Hebrew University of Jerusalem, Israel
    • S. Hart. Adaptive heuristics. Technical Report DP-372, Center for Rationality, The Hebrew University of Jerusalem, Israel, 2004.
    • (2004) Adaptive heuristics
    • Hart, S.1
  • 145
    • 0000908510 scopus 로고    scopus 로고
    • A simple adaptive procedure leading to correlated equilibrium
    • S. Hart and A. Mas-Colell. A simple adaptive procedure leading to correlated equilibrium. Econometrica, 68:1127-1150, 2000.
    • (2000) Econometrica , vol.68 , pp. 1127-1150
    • Hart, S.1    Mas-Colell, A.2
  • 148
    • 2942744741 scopus 로고    scopus 로고
    • Uncoupled dynamics do not lead to Nash Equilibrium
    • S. Hart and A. Mas-Colell. Uncoupled dynamics do not lead to Nash equilibrium. American Economic Review, 93:1830-1836, 2003.
    • (2003) American Economic Review , vol.93 , pp. 1830-1836
    • Hart, S.1    Mas-Colell, A.2
  • 151
    • 0032164946 scopus 로고    scopus 로고
    • Sequential prediction of individual sequences under general loss functions
    • D. Haussler, J. Kivinen, and M. Warmuth. Sequential prediction of individual sequences under general loss functions. IEEE Transactions on Information Theory, 44:1906-1925, 1998.
    • (1998) IEEE Transactions on Information Theory , vol.44 , pp. 1906-1925
    • Haussler, D.1    Kivinen, J.2    Warmuth, M.3
  • 152
    • 0031326925 scopus 로고    scopus 로고
    • Mutual information, metric entropy and cumulative relative entropy risk
    • D. Haussler and M. Opper. Mutual information, metric entropy and cumulative relative entropy risk. The Annals of Statistics, 25:2451-2492, 1997.
    • (1997) The Annals of Statistics , vol.25 , pp. 2451-2492
    • Haussler, D.1    Opper, M.2
  • 156
    • 0031122905 scopus 로고    scopus 로고
    • Predicting nearly as well as the best pruning of a decision tree
    • D.P. Helmbold and R. Schapire. Predicting nearly as well as the best pruning of a decision tree. Machine Learning, 27(1):51-68, 1997.
    • (1997) Machine Learning , vol.27 , Issue.1 , pp. 51-68
    • Helmbold, D.P.1    Schapire, R.2
  • 157
    • 0031122868 scopus 로고    scopus 로고
    • A comparison of new and old algorithms for a mixture estimation problem
    • D.P. Helmbold, R. Schapire, Y. Singer, and M. Warmuth. A comparison of new and old algorithms for a mixture estimation problem. Machine Learning, 27(1):97-119, 1997.
    • (1997) Machine Learning , vol.27 , Issue.1 , pp. 97-119
    • Helmbold, D.P.1    Schapire, R.2    Singer, Y.3    Warmuth, M.4
  • 159
    • 0032137328 scopus 로고    scopus 로고
    • Tracking the best expert
    • D.P. Helmbold and M. Warmuth. Tracking the best expert. Machine Learning, 32(2):151-178, 1998.
    • (1998) Machine Learning , vol.32 , Issue.2 , pp. 151-178
    • Helmbold, D.P.1    Warmuth, M.2
  • 161
  • 162
    • 84942484786 scopus 로고
    • Ridge regression: Biased estimation for nonorthogonal problems
    • A. Hoerl and R. Kennard. Ridge regression: Biased estimation for nonorthogonal problems. Technometrics, 12:55-67, 1970.
    • (1970) Technometrics , vol.12 , pp. 55-67
    • Hoerl, A.1    Kennard, R.2
  • 163
    • 0036436650 scopus 로고    scopus 로고
    • On the global convergence of stochastic fictitious play
    • J. Hofbauer and W.H. Sandholm. On the global convergence of stochastic fictitious play. Econometrica, 70:2265-2294, 2002.
    • (2002) Econometrica , vol.70 , pp. 2265-2294
    • Hofbauer, J.1    Sandholm, W.H.2
  • 165
    • 21844465698 scopus 로고    scopus 로고
    • Adaptive online prediction by following the perturbed leader
    • M. Hutter and J. Poland. Adaptive online prediction by following the perturbed leader. Journal of Machine Learning Research, 6:639-660, 2005.
    • (2005) Journal of Machine Learning Research , vol.6 , pp. 639-660
    • Hutter, M.1    Poland, J.2
  • 166
    • 17444429676 scopus 로고    scopus 로고
    • Universal investment in markets with transaction costs
    • G. Iyengar. Universal investment in markets with transaction costs. Mathematical Finance, 15:359-371, 2005.
    • (2005) Mathematical Finance , vol.15 , pp. 359-371
    • Iyengar, G.1
  • 167
    • 0034316566 scopus 로고    scopus 로고
    • Growth optimal investment in horse race markets with costs
    • G. Iyengar and T. Cover. Growth optimal investment in horse race markets with costs. IEEE Transactions on Information Theory, 46:2675-2683, 2000.
    • (2000) IEEE Transactions on Information Theory , vol.46 , pp. 2675-2683
    • Iyengar, G.1    Cover, T.2
  • 168
    • 27644583858 scopus 로고    scopus 로고
    • A combinatorial problem arising in information theory: Precise minimax redundancy for markov sources
    • Trends in Mathematics, Birkhauser, Basel
    • P. Jacquet and W. Szpankowski. A combinatorial problem arising in information theory: Precise minimax redundancy for Markov sources. In Mathematics and Computer science II (Versailles, 2002), Trends in Mathematics, pp. 311-328. Birkhauser, Basel, 2002.
    • (2002) Mathematics and Computer Science II (Versailles, 2002 , pp. 311-328
    • Jacquet, P.1    Szpankowski, W.2
  • 169
    • 0002298153 scopus 로고
    • Bayesian learning in normal form games
    • J.S. Jordan. Bayesian learning in normal form games. Games and Economic Behavior, 3:60-81, 1991.
    • (1991) Games and Economic Behavior , vol.3 , pp. 60-81
    • Jordan, J.S.1
  • 170
    • 0002672797 scopus 로고
    • Bayesian learning in repeated games
    • J.S. Jordan. Bayesian learning in repeated games. Games and Economic Behavior, 9:8-20, 1995.
    • (1995) Games and Economic Behavior , vol.9 , pp. 8-20
    • Jordan, J.S.1
  • 173
    • 33846955531 scopus 로고    scopus 로고
    • Online bounds for Bayesian algorithms
    • L.K. Saul, Y. Weiss, and L. Bottou, MIT Press, Cambridge, MA
    • S. Kakade and A.Y. Ng. Online bounds for Bayesian algorithms. In L.K. Saul, Y. Weiss, and L. Bottou, ed., Advances in Neural Information Processing Systems 17, pp. 641-648. MIT Press, Cambridge, MA, 2005.
    • (2005) Advances in Neural Information Processing Systems , vol.7 , pp. 641-648
    • Kakade, S.1    Ng, A.Y.2
  • 176
    • 0000221289 scopus 로고
    • Rational learning leads to Nash equilibrium
    • E. Kalai and E. Lehrer. Rational learning leads to Nash equilibrium. Econometrica, 61:1019— 1045, 1993.
    • (1993) Econometrica , vol.61 , pp. 1045
    • Kalai, E.1    Lehrer, E.2
  • 178
    • 22944453697 scopus 로고    scopus 로고
    • A criterion for the existence of predictive complexity for binary games
    • Lecture Notes in Artificial Intelligence 3244, Springer, Heidelberg, Germany
    • Y. Kalnishkan, V. Vovk, and M.V. Vyugin. A criterion for the existence of predictive complexity for binary games. In Proceedings of the 15th International Conference on Algorithmic Learning Theory, pp. 249-263. Lecture Notes in Artificial Intelligence 3244, Springer, Heidelberg, Germany, 2004.
    • (2004) Proceedings of the 15th International Conference on Algorithmic Learning Theory , pp. 249-263
    • Kalnishkan, Y.1    Vovk, V.2    Vyugin, M.V.3
  • 180
    • 0000733254 scopus 로고
    • A new interpretation of information rate
    • J.L. Kelly. A new interpretation of information rate. Bell System Technical Journal, 35:917-926, 1956.
    • (1956) Bell System Technical Journal , vol.35 , pp. 917-926
    • Kelly, J.L.1
  • 181
    • 0008815681 scopus 로고    scopus 로고
    • Exponentiated gradient versus gradient descent for linear predictors
    • J. Kivinen and M. Warmuth. Exponentiated gradient versus gradient descent for linear predictors. Information and Computation, 132(1):1-63, 1997.
    • (1997) Information and Computation , vol.132 , Issue.1 , pp. 1-63
    • Kivinen, J.1    Warmuth, M.2
  • 183
    • 0035575628 scopus 로고    scopus 로고
    • Relative loss bounds for multidimensional regression problems
    • J. Kivinen and M. Warmuth. Relative loss bounds for multidimensional regression problems. Machine Learning, 45(3):301-329, 2001.
    • (2001) Machine Learning , vol.45 , Issue.3 , pp. 301-329
    • Kivinen, J.1    Warmuth, M.2
  • 184
    • 0031375503 scopus 로고    scopus 로고
    • The Perceptron algorithm vs. Winnow: Linear vs. Logarithmic mistake bounds when few input variables are relevant
    • J. Kivinen, M. Warmuth, and P. Auer. The Perceptron algorithm vs. Winnow: Linear vs. logarithmic mistake bounds when few input variables are relevant. Artificial Intelligence, 97:325-343, 1997.
    • (1997) Artificial Intelligence , vol.97 , pp. 325-343
    • Kivinen, J.1    Warmuth, M.2    Auer, P.3
  • 185
    • 0001902056 scopus 로고
    • Three approaches to the definition of the concept “quantity of information.”
    • N.A. Kolmogorov. Three approaches to the definition of the concept “quantity of information.”. Problems of Information Transmission, 1:3-11, 1965.
    • (1965) Problems of Information Transmission , vol.1 , pp. 3-11
    • Kolmogorov, N.A.1
  • 189
    • 0002899547 scopus 로고
    • Asymptotically efficient adaptive allocation rules
    • T.L. Lai and H. Robbins. Asymptotically efficient adaptive allocation rules. Advances in Applied Mathematics, 6:4-22, 1985.
    • (1985) Advances in Applied Mathematics , vol.6 , pp. 4-22
    • Lai, T.L.1    Robbins, H.2
  • 191
    • 0000258837 scopus 로고
    • Least squares estimates in stochastic regression models with applications to identification and control of dynamic systems
    • T.L. Lai and C.Z. Wei. Least squares estimates in stochastic regression models with applications to identification and control of dynamic systems. The Annals of Statistics, 10(1):154-166, 1982.
    • (1982) The Annals of Statistics , vol.10 , Issue.1 , pp. 154-166
    • Lai, T.L.1    Wei, C.Z.2
  • 193
    • 0037609356 scopus 로고    scopus 로고
    • Approachability in infinite dimensional spaces
    • E. Lehrer. Approachability in infinite dimensional spaces. International Journal of Game Theory, 31:255-270, 1997.
    • (1997) International Journal of Game Theory , vol.31 , pp. 255-270
    • Lehrer, E.1
  • 194
    • 0001105122 scopus 로고    scopus 로고
    • Any inspection is manipulable
    • E. Lehrer. Any inspection is manipulable. Econometrica, 69:1333-1347, 2001.
    • (2001) Econometrica , vol.69 , pp. 1333-1347
    • Lehrer, E.1
  • 195
    • 0038404996 scopus 로고    scopus 로고
    • A wide range no-regret theorem
    • E. Lehrer. A wide range no-regret theorem. Games and Economic Behavior, 42:101-115, 2003.
    • (2003) Games and Economic Behavior , vol.42 , pp. 101-115
    • Lehrer, E.1
  • 196
    • 0346359481 scopus 로고    scopus 로고
    • Merging and learning
    • IMS Lecture Notes Monograph Series, Institute of Mathematical Statistics, Hayward, CA
    • E. Lehrer and R. Smorodinsky. Merging and learning. In Statistics, Probability and Game Theory, IMS Lecture Notes Monograph Series 30, pp. 147-168. Institute of Mathematical Statistics, Hayward, CA, 1996.
    • (1996) Statistics, Probability and Game Theory , vol.30 , pp. 147-168
    • Lehrer, E.1    Smorodinsky, R.2
  • 199
    • 0036161258 scopus 로고    scopus 로고
    • The relaxed online maximum margin algorithm
    • Y. Li and P.M. Long. The relaxed online maximum margin algorithm. Machine Learning,46(1/3):361-387, 2002.
    • (2002) Machine Learning , vol.46 , Issue.1-3 , pp. 361-387
    • Li, Y.1    Long, P.M.2
  • 200
    • 34250091945 scopus 로고
    • Learning quickly when irrelevant attributes abound: A new linear-threshold algorithm
    • N. Littlestone. Learning quickly when irrelevant attributes abound: A new linear-threshold algorithm. Machine Learning, 2(4):285-318, 1988.
    • (1988) Machine Learning , vol.2 , Issue.4 , pp. 285-318
    • Littlestone, N.1
  • 201
    • 0000511449 scopus 로고
    • Redundant noisy attributes, attribute errors, and linear threshold learning using Winnow
    • Morgan Kaufmann, San Mateo, CA
    • N. Littlestone. Redundant noisy attributes, attribute errors, and linear threshold learning using Winnow. In Proceedings of the 4th Annual Workshop on Computational Learning Theory, pp. 147-156. Morgan Kaufmann, San Mateo, CA, 1991.
    • (1991) Proceedings of the 4th Annual Workshop on Computational Learning Theory , pp. 147-156
    • Littlestone, N.1
  • 204
    • 0000118014 scopus 로고
    • On bounded bilinear forms in an infinite number of variables
    • J.E. Littlewood. On bounded bilinear forms in an infinite number of variables. Quarterly Journal of Mathematics (Oxford) 1, pp. 164-174, 1930.
    • (1930) Quarterly Journal of Mathematics (Oxford , vol.1 , pp. 164-174
    • Littlewood, J.E.1
  • 206
    • 0005375288 scopus 로고    scopus 로고
    • Pattern classification and learning theory
    • L. Györfi, Springer
    • G. Lugosi. Pattern classification and learning theory. In L. Gyoörfi, ed., Principles of Nonparametric Learning, pp. 5-62. Springer, 2002.
    • (2002) Principles of Nonparametric Learning , pp. 5-62
    • Lugosi, G.1
  • 207
    • 0001784922 scopus 로고    scopus 로고
    • Efficient learning with virtual threshold gates
    • W. Maass and M. Warmuth. Efficient learning with virtual threshold gates. Information and Computation, 141(1):66-83, 1998.
    • (1998) Information and Computation , vol.141 , Issue.1 , pp. 66-83
    • Maass, W.1    Warmuth, M.2
  • 209
  • 210
    • 0001725820 scopus 로고
    • Perturbation des methodes d'optimisation
    • B. Martinet. Perturbation des methodes d'optimisation. Applications. RAIRO Analyse Numerique, 12:153-171, 1978.
    • (1978) RAIRO Analyse Numerique , vol.12 , pp. 153-171
    • Martinet, B.1
  • 211
    • 9444257628 scopus 로고    scopus 로고
    • Online geometric optimization in the bandit setting against an adaptive adversary
    • Springer, New York
    • H.B. McMahan and A. Blum. Online geometric optimization in the bandit setting against an adaptive adversary. In Proceedings of the 17th Annual Conference on Learning Theory, pp. 109-123. Springer, New York, 2004
    • (2004) Proceedings of the 17th Annual Conference on Learning Theory , pp. 109-123
    • McMahan, H.B.1    Blum, A.2
  • 212
    • 0038675791 scopus 로고
    • On repeated games with incomplete information played by non-Bayesian players
    • N. Megiddo. On repeated games with incomplete information played by non-Bayesian players. International Journal of Game Theory, 9:157-167, 1980.
    • (1980) International Journal of Game Theory , vol.9 , pp. 157-167
    • Megiddo, N.1
  • 213
    • 0027632407 scopus 로고
    • Universal schemes for sequential decision from individual data sequences
    • N. Merhav and M. Feder. Universal schemes for sequential decision from individual data sequences. IEEE Transactions on Information Theory, 39(4):1280-1292, 1993.
    • (1993) IEEE Transactions on Information Theory , vol.39 , Issue.4 , pp. 1280-1292
    • Merhav, N.1    Feder, M.2
  • 216
    • 0003351019 scopus 로고
    • Repeated games
    • Papers 9420, 9421, 9422. Louvain-la-Neuve, Belgium
    • J.-F. Mertens, S. Sorin, and S. Zamir. Repeated games. CORE Discussion papers 9420, 9421, 9422. Louvain-la-Neuve, Belgium, 1994.
    • (1994) CORE Discussion
    • Mertens, J.-F.1    Sorin, S.2    Zamir, S.3
  • 219
    • 0141425904 scopus 로고    scopus 로고
    • Semiring frameworks and algorithms for shortest-distance problems
    • M. Mohri. Semiring frameworks and algorithms for shortest-distance problems. Journal of Automata, Languages and Combinatorics, 7:321-350, 2002.
    • (2002) Journal of Automata, Languages and Combinatorics , vol.7 , pp. 321-350
    • Mohri, M.1
  • 220
    • 0029690246 scopus 로고    scopus 로고
    • Fictitious play property for games with identical interests
    • D. Monderer and L. Shapley. Fictitious play property for games with identical interests. Journal of Economic Theory, 68:258-265, 1996.
    • (1996) Journal of Economic Theory , vol.68 , pp. 258-265
    • Monderer, D.1    Shapley, L.2
  • 221
    • 0000927072 scopus 로고    scopus 로고
    • Prediction, optimization, and learning in repeated games
    • J.H. Nachbar. Prediction, optimization, and learning in repeated games. Econometrica, 65:275-309, 1997.
    • (1997) Econometrica , vol.65 , pp. 275-309
    • Nachbar, J.H.1
  • 222
    • 0001730497 scopus 로고
    • Non-cooperative games
    • J. Nash. Non-cooperative games. Annals of Mathematics, 54:286-295, 1951.
    • (1951) Annals of Mathematics , vol.54 , pp. 286-295
    • Nash, J.1
  • 229
    • 0032208221 scopus 로고    scopus 로고
    • The cost of achieving the best portfolio in hindsight
    • E. Ordentlich and T. Cover. The cost of achieving the best portfolio in hindsight. Mathematics of Operations Research, 23:960-982, 1998.
    • (1998) Mathematics of Operations Research , vol.23 , pp. 960-982
    • Ordentlich, E.1    Cover, T.2
  • 233
    • 0032595782 scopus 로고    scopus 로고
    • An efficient extension to mixture techniques for prediction and decision trees
    • F. Pereira and Y. Singer. An efficient extension to mixture techniques for prediction and decision trees. Machine Learning, 36:183-199, 1999.
    • (1999) Machine Learning , vol.36 , pp. 183-199
    • Pereira, F.1    Singer, Y.2
  • 235
    • 0000065961 scopus 로고
    • Some applications of the metric entropy condition to harmonic analysis
    • LectureNotes in Mathematics, Springer
    • G. Pisier. Some applications of the metric entropy condition to harmonic analysis. In Banach Spaces, Harmonic Analysis, and Probability Theory. Lecture Notes in Mathematics 995, pp. 123-154. Springer, 1983.
    • (1983) Banach Spaces, Harmonic Analysis, and Probability Theory , vol.995 , pp. 123-154
    • Pisier, G.1
  • 236
    • 0000506580 scopus 로고
    • Generalized Kraft's inequality and arithmetic coding
    • J. Rissanen. Generalized Kraft's inequality and arithmetic coding. IBM Journal of Research and Development, 20:198-203, 1976.
    • (1976) IBM Journal of Research and Development , vol.20 , pp. 198-203
    • Rissanen, J.1
  • 237
    • 0018015137 scopus 로고
    • Modeling by shortest data description
    • J. Rissanen. Modeling by shortest data description. Automatica, 14:465-471, 1978.
    • (1978) Automatica , vol.14 , pp. 465-471
    • Rissanen, J.1
  • 238
    • 0021466584 scopus 로고
    • Universal coding, information, prediction and estimation
    • J. Rissanen. Universal coding, information, prediction and estimation. IEEE Transactions on Information Theory, 30:629-636, 1984.
    • (1984) IEEE Transactions on Information Theory , vol.30 , pp. 629-636
    • Rissanen, J.1
  • 239
    • 0022754340 scopus 로고
    • Complexity of strings in the class of Markov sources
    • J. Rissanen. Complexity of strings in the class of Markov sources. IEEE Transactions on Information Theory, 32:526-532, 1986.
    • (1986) IEEE Transactions on Information Theory , vol.32 , pp. 526-532
    • Rissanen, J.1
  • 240
    • 0000318553 scopus 로고
    • Stochastic complexity and modeling
    • J. Rissanen. Stochastic complexity and modeling. The Annals of Statistics, 14(3):1080-1100, 1986.
    • (1986) The Annals of Statistics , vol.14 , Issue.3 , pp. 1080-1100
    • Rissanen, J.1
  • 244
    • 0011026447 scopus 로고
    • Asymptotically subminimax solutions of compound statistical decision problems
    • University of California Press, Berkeley, CA
    • H. Robbins. Asymptotically subminimax solutions of compound statistical decision problems. In Proceedings of the Second Berkeley Symposium on Mathematical Statistics and Probability, pp. 131-148. University of California Press, Berkeley, CA, 1951.
    • (1951) Proceedings of the Second Berkeley Symposium on Mathematical Statistics and Probability , pp. 131-148
    • Robbins, H.1
  • 245
  • 246
    • 0001402950 scopus 로고
    • An iterative method of solving a game
    • J. Robinson. An iterative method of solving a game. Annals of Mathematics, 54:296-301, 1951.
    • (1951) Annals of Mathematics , vol.54 , pp. 296-301
    • Robinson, J.1
  • 247
    • 0004267646 scopus 로고
    • Princeton University Press, Princeton, NJ
    • R.T. Rockafellar. Convex Analysis. Princeton University Press, Princeton, NJ, 1970.
    • (1970) Convex Analysis
    • Rockafellar, R.T.1
  • 248
    • 0016985417 scopus 로고
    • Monotone operators and the proximal point algorithm
    • R.T. Rockafellar. Monotone operators and the proximal point algorithm. SIAM Journal on Control and Optimization, 14(1):877-898, 1976.
    • (1976) SIAM Journal on Control and Optimization , vol.14 , Issue.1 , pp. 877-898
    • Rockafellar, R.T.1
  • 249
    • 11144273669 scopus 로고
    • The perceptron: A probabilistic model for information storage and organization in the brain
    • F. Rosenblatt. The Perceptron: A probabilistic model for information storage and organization in the brain. Psychological Review, 65:386-408, 1958.
    • (1958) Psychological Review , vol.65 , pp. 386-408
    • Rosenblatt, F.1
  • 251
    • 0013327190 scopus 로고    scopus 로고
    • Minimizing regret: The general case
    • A. Rustichini. Minimizing regret: The general case. Games and Economic Behavior, 29:224-243, 1999.
    • (1999) Games and Economic Behavior , vol.29 , pp. 224-243
    • Rustichini, A.1
  • 253
    • 0024097061 scopus 로고
    • Prediction of random sequences and universal coding
    • B.Ya. Ryabko. Prediction of random sequences and universal coding. Problems of Information Transmission, 24:87-96, 1988.
    • (1988) Problems of Information Transmission , vol.24 , pp. 87-96
    • Ryabko, B.1
  • 254
    • 0001402719 scopus 로고
    • The sequential compound decision problem with m × n finite loss matrix
    • J. Van Ryzin. The sequential compound decision problem with m × n finite loss matrix. Annals of Mathematical Statistics, 37:954-975, 1966.
    • (1966) Annals of Mathematical Statistics , vol.37 , pp. 954-975
    • Van Ryzin, J.1
  • 256
    • 0003389747 scopus 로고
    • Asymptotic solutions of the sequential compound decision problem
    • E. Samuel. Asymptotic solutions of the sequential compound decision problem. Annals of Mathematical Statistics, 34:1079-1094, 1963.
    • (1963) Annals of Mathematical Statistics , vol.34 , pp. 1079-1094
    • Samuel, E.1
  • 257
    • 0004637310 scopus 로고
    • Convergence of the losses of certain decision rules for the sequential compound decision problem
    • E. Samuel. Convergence of the losses of certain decision rules for the sequential compound decision problem. Annals of Mathematical Statistics, 35:1606-1621, 1964.
    • (1964) Annals of Mathematical Statistics , vol.35 , pp. 1606-1621
    • Samuel, E.1
  • 264
    • 0001899764 scopus 로고
    • Probability inequalities for the sum in sampling without replacement
    • R.J. Serfling. Probability inequalities for the sum in sampling without replacement. Annals of Statistics, 2:39-48, 1974.
    • (1974) Annals of Statistics , vol.2 , pp. 39-48
    • Serfling, R.J.1
  • 266
    • 84972576948 scopus 로고
    • A combinatorial problem: Stability and order for models and theories in infinitary languages
    • S. Shelah. A combinatorial problem: Stability and order for models and theories in infinitary languages. Pacific Journal of Mathematics, 41:247-261, 1972.
    • (1972) Pacific Journal of Mathematics , vol.41 , pp. 247-261
    • Shelah, S.1
  • 271
  • 272
    • 0010956944 scopus 로고
    • Distribution inequalities for the binomial law
    • E.V. Slud. Distribution inequalities for the binomial law. Annals of Probability, 5:404-412, 1977.
    • (1977) Annals of Probability , vol.5 , pp. 404-412
    • Slud, E.V.1
  • 274
    • 4544279425 scopus 로고
    • A formal theory of inductive inference, part I
    • R. Solomonoff. A formal theory of inductive inference, part I. Information and Control, 7:1-22, 1964.
    • (1964) Information and Control , vol.7 , pp. 1-22
    • Solomonoff, R.1
  • 275
    • 50549204079 scopus 로고
    • A formal theory of inductive inference, part II
    • R. Solomonoff. A formal theory of inductive inference, part II. Information and Control, 7:224-254, 1964.
    • (1964) Information and Control , vol.7 , pp. 224-254
    • Solomonoff, R.1
  • 277
    • 0025399335 scopus 로고
    • Probabilistic neural networks and the polynomial Adaline as complementary techniques for classification
    • D.F. Specht. Probabilistic neural networks and the polynomial Adaline as complementary techniques for classification. IEEE Transactions on Neural Networks, 1:111-121, 1990.
    • (1990) IEEE Transactions on Neural Networks , vol.1 , pp. 111-121
    • Specht, D.F.1
  • 279
    • 21244487467 scopus 로고    scopus 로고
    • Internal regret in on-line portfolio selection
    • G. Stoltz and G. Lugosi. Internal regret in on-line portfolio selection. Machine Learning, 59:125-159, 2005.
    • (2005) Machine Learning , vol.59 , pp. 125-159
    • Stoltz, G.1    Lugosi, G.2
  • 280
    • 0009919767 scopus 로고
    • Gaussian measures, Cauchy measures and ɛ-entropy
    • V.N. Sudakov. Gaussian measures, Cauchy measures and ɛ-entropy. Soviet Mathematics Doklady, 10:310-313, 1969.
    • (1969) Soviet Mathematics Doklady , vol.10 , pp. 310-313
    • Sudakov, V.N.1
  • 281
    • 0000913075 scopus 로고
    • On the best constants in the Khintchine inequality
    • S.J. Szarek. On the best constants in the Khintchine inequality. Studia Mathematica, 63:197-208, 1976.
    • (1976) Studia Mathematica , vol.63 , pp. 197-208
    • Szarek, S.J.1
  • 282
    • 0002138891 scopus 로고    scopus 로고
    • On asymptotics of certain recurrences arising in universal coding
    • W. Szpankowski. On asymptotics of certain recurrences arising in universal coding. Problems of Information Transmission, 34:142-146, 1998.
    • (1998) Problems of Information Transmission , vol.34 , pp. 142-146
    • Szpankowski, W.1
  • 283
    • 0034925309 scopus 로고    scopus 로고
    • Predicting nearly as well as the best pruning of a decision tree through dynamic programming scheme
    • E. Takimoto, A. Maruoka, and V. Vovk. Predicting nearly as well as the best pruning of a decision tree through dynamic programming scheme. Theoretical Computer Science, 261:179-209, 2001.
    • (2001) Theoretical Computer Science , vol.261 , pp. 179-209
    • Takimoto, E.1    Maruoka, A.2    Vovk, V.3
  • 285
    • 0037120731 scopus 로고    scopus 로고
    • Predicting nearly as well as the best pruning of a planar decision graph
    • E. Takimoto and M. Warmuth. Predicting nearly as well as the best pruning of a planar decision graph. Theoretical Computer Science, 288:217-235, 2002.
    • (2002) Theoretical Computer Science , vol.288 , pp. 217-235
    • Takimoto, E.1    Warmuth, M.2
  • 287
    • 0002662601 scopus 로고
    • Regularity of Gaussian processes
    • M. Talagrand. Regularity of Gaussian processes. Acta Mathematica, 159:99-149, 1987.
    • (1987) Acta Mathematica , vol.159 , pp. 99-149
    • Talagrand, M.1
  • 289
    • 0003007938 scopus 로고    scopus 로고
    • Support vector machine active learning with applications to text classification
    • MorganKaufmann, San Mateo, CA
    • S. Tong and D. Koller. Support vector machine active learning with applications to text classification. In Proceedings of the 17th International Conference on Machine Learning, pp. 999-1006. Morgan Kaufmann, San Mateo, CA, 2000.
    • (2000) Proceedings of the 17th International Conference on Machine Learning , pp. 999-1006
    • Tong, S.1    Koller, D.2
  • 290
    • 0027607344 scopus 로고
    • On the convergence of the exponential multiplier method for convex programming
    • P. Tseng and D.P. Bertsekas. On the convergence of the exponential multiplier method for convex programming. Mathematical Programming, 60:1-19, 1993.
    • (1993) Mathematical Programming , vol.60 , pp. 1-19
    • Tseng, P.1    Bertsekas, D.P.2
  • 293
    • 0001024505 scopus 로고
    • On the uniform convergence of relative frequencies of events to their probabilities
    • V.N. Vapnik and A.Ya. Chervonenkis. On the uniform convergence of relative frequencies of events to their probabilities. Theory of Probability and Its Applications, 16:264-280, 1971.
    • (1971) Theory of Probability and Its Applications , vol.16 , pp. 264-280
    • Vapnik, V.N.1    Chervonenkis, A.2
  • 294
    • 0010864753 scopus 로고
    • Pattern recognition using generalized portrait method
    • V.N. Vapnik and A. Lerner. Pattern recognition using generalized portrait method. Automation and Remote Control, 24:774-780, 1963.
    • (1963) Automation and Remote Control , vol.24 , pp. 774-780
    • Vapnik, V.N.1    Lerner, A.2
  • 298
    • 0032047115 scopus 로고    scopus 로고
    • A game of prediction with expert advice
    • V. Vovk. A game of prediction with expert advice. Journal of Computer and System Sciences, 56(2):153-173, 1998.
    • (1998) Journal of Computer and System Sciences , vol.56 , Issue.2 , pp. 153-173
    • Vovk, V.1
  • 299
    • 0032652062 scopus 로고    scopus 로고
    • Derandomizing stochastic prediction strategies
    • V. Vovk. Derandomizing stochastic prediction strategies. Machine Learning, 35(3):247-282, 1999.
    • (1999) Machine Learning , vol.35 , Issue.3 , pp. 247-282
    • Vovk, V.1
  • 300
    • 0035413537 scopus 로고    scopus 로고
    • Competitive on-line statistics
    • V. Vovk. Competitive on-line statistics. International Statistical Review, 69:213-248, 2001.
    • (2001) International Statistical Review , vol.69 , pp. 213-248
    • Vovk, V.1
  • 304
    • 0036160918 scopus 로고    scopus 로고
    • Iterative nonparametric estimation of a log-optimal portfolio selection function
    • H. Walk and S. Yakowitz. Iterative nonparametric estimation of a log-optimal portfolio selection function. IEEE Transactions on Information Theory, 48:324-333, 2002.
    • (2002) IEEE Transactions on Information Theory , vol.48 , pp. 324-333
    • Walk, H.1    Yakowitz, S.2
  • 306
    • 0142227382 scopus 로고    scopus 로고
    • Technical Report CSD-TR-98-07, Department of Computer Science, Royal Holloway College, University of London
    • C. Watkins. Kernels from matching operations. Technical Report CSD-TR-98-07, Department of Computer Science, Royal Holloway College, University of London, 1999.
    • (1999) Kernels from Matching Operations
    • Watkins, C.1
  • 308
    • 0035443342 scopus 로고    scopus 로고
    • Universal prediction of binary individual sequences in the presence of noise
    • T. Weissman and N. Merhav. Universal prediction of binary individual sequences in the presence of noise. IEEE Transactions on Information Theory, 47:2151-2173, 2001.
    • (2001) IEEE Transactions on Information Theory , vol.47 , pp. 2151-2173
    • Weissman, T.1    Merhav, N.2
  • 309
    • 0035397523 scopus 로고    scopus 로고
    • Twofold universal prediction schemes for achieving the finite state predictability of a noisy individual binary sequence
    • T. Weissman, N. Merhav, and Somekh-Baruch. Twofold universal prediction schemes for achieving the finite state predictability of a noisy individual binary sequence. IEEE Transactions on Information Theory, 47:1849-1866, 2001.
    • (2001) IEEE Transactions on Information Theory , vol.47 , pp. 1849-1866
    • Weissman, T.1    Merhav, N.2
  • 312
    • 0033901631 scopus 로고    scopus 로고
    • Asymptotic minimax loss for data compression, gambling, and prediction
    • Q. Xie and A. Barron. Asymptotic minimax loss for data compression, gambling, and prediction. IEEE Transactions on Information Theory, 46:431-445, 2000.
    • (2000) IEEE Transactions on Information Theory , vol.46 , pp. 431-445
    • Xie, Q.1    Barron, A.2
  • 313
    • 0032121805 scopus 로고    scopus 로고
    • A decision-theoretic extension of stochastic complexity and its application to learning
    • New York
    • K. Yamanishi. A decision-theoretic extension of stochastic complexity and its application to learning. IEEE Transactions on Information Theory, 44:1424-1440, New York, 1998.
    • (1998) IEEE Transactions on Information Theory , vol.44 , pp. 1424-1440
    • Yamanishi, K.1
  • 314
    • 0031630775 scopus 로고    scopus 로고
    • Minimax relative loss analysis for sequential prediction algorithms using parametric hypothesis
    • ACM Press, New York
    • K. Yamanishi. Minimax relative loss analysis for sequential prediction algorithms using parametric hypothesis. In Proceedings of the 11th Annual Conference on Computational Learning Theory, pp. 32-43. ACM Press, New York, 1998.
    • (1998) Proceedings of the 11th Annual Conference on Computational Learning Theory , pp. 32-43
    • Yamanishi, K.1
  • 315
    • 3543088062 scopus 로고    scopus 로고
    • How to better use expert advice
    • New York
    • R. Yaroshinsky, R. El-Yaniv, and S. Seiden. How to better use expert advice. Machine Learning, 55(3):271-309, New York, 2004.
    • (2004) Machine Learning , vol.55 , Issue.3 , pp. 271-309
    • Yaroshinsky, R.1    El-Yaniv, R.2    Seiden, S.3
  • 317
    • 0017996424 scopus 로고
    • Coding theorems for individual sequences
    • J. Ziv. Coding theorems for individual sequences. IEEE Transactions on Information Theory,24:405-412, 1978.
    • (1978) IEEE Transactions on Information Theory , vol.24 , pp. 405-412
    • Ziv, J.1
  • 318
    • 0018995553 scopus 로고
    • Distortion-rate theory for individual sequences
    • J. Ziv. Distortion-rate theory for individual sequences. IEEE Transactions on Information Theory, 26:137-143, 1980.
    • (1980) IEEE Transactions on Information Theory , vol.26 , pp. 137-143
    • Ziv, J.1
  • 319
    • 0017493286 scopus 로고
    • A universal algorithm for sequential data-compression
    • J. Ziv and A. Lempel. A universal algorithm for sequential data-compression. IEEE Transactions on Information Theory, 23:337-343, 1977.
    • (1977) IEEE Transactions on Information Theory , vol.23 , pp. 337-343
    • Ziv, J.1    Lempel, A.2
  • 320
    • 77951203397 scopus 로고
    • The complexity of finite objects and the development of the concepts of information and randomness by means of the theory of algorithms
    • A.K. Zvonkin and L.A. Levin. The complexity of finite objects and the development of the concepts of information and randomness by means of the theory of algorithms. Russian Mathematical Surveys, 25:83-124, 1970.
    • (1970) Russian Mathematical Surveys , vol.25 , pp. 83-124
    • Zvonkin, A.K.1    Levin, L.A.2


* 이 정보는 Elsevier사의 SCOPUS DB에서 KISTI가 분석하여 추출한 것입니다.