메뉴 건너뛰기




Volumn 47, Issue 3, 2010, Pages 369-401

Machine learning problems from optimization perspective

Author keywords

Automatic model selection; Bayesian Ying Yang learning; Convex duality; Convex programming; Learning versus optimization; Local convexity; Model selection; Parameter learning; Three levels of inverse problems

Indexed keywords

AUTOMATIC MODEL SELECTION; BAYESIAN YING-YANG LEARNING; CONVEX DUALITY; CONVEX PROGRAMMING; LOCAL CONVEXITY; MODEL SELECTION;

EID: 77954757210     PISSN: 09255001     EISSN: 15732916     Source Type: Journal    
DOI: 10.1007/s10898-008-9364-0     Document Type: Article
Times cited : (10)

References (59)
  • 1
    • 0016355478 scopus 로고
    • A new look at the statistical model identification
    • Akaike, H.: A new look at the statistical model identification. IEEE Trans. Autom. Control 19, 714-723 (1974)
    • (1974) IEEE Trans. Autom. Control , vol.19 , pp. 714-723
    • Akaike, H.1
  • 2
    • 21144438166 scopus 로고
    • Likelihood of a model and information criteria
    • Akaike, H.: Likelihood of a model and information criteria. J. Econom. 16, 3-14 (1981)
    • (1981) J. Econom , vol.16 , pp. 3-14
    • Akaike, H.1
  • 3
    • 33749754615 scopus 로고    scopus 로고
    • A New Learning Algorithm for Blind Signal Separation
    • MIT Press
    • Amari, S., Cichocki, A., Yang, H.: A New Learning Algorithm for Blind Signal Separation. Advances in NIPS, 8, pp. 757-763. MIT Press (1996)
    • (1996) Advances in NIPS , vol.8 , pp. 757-763
    • Amari, S.1    Cichocki, A.2    Yang, H.3
  • 4
    • 0035135850 scopus 로고    scopus 로고
    • Aglobally convergent Lagrange and barrier function iterative algorithm for the traveling salesman problem
    • Dang, C., Xu, L.: Aglobally convergent Lagrange and barrier function iterative algorithm for the traveling salesman problem. Neural Netw. 14 (2), 217-230 (2001)
    • (2001) Neural Netw , vol.14 , Issue.2 , pp. 217-230
    • Dang, C.1    Xu, L.2
  • 5
    • 0038893802 scopus 로고    scopus 로고
    • A Lagrange multiplier and Hopfield-type barrier function method for the traveling salesman problem
    • Dang, C., Xu, L.: A Lagrange multiplier and Hopfield-type barrier function method for the traveling salesman problem.. Neural Comput. 14 (2), 303-324 (2001)
    • (2001) Neural Comput , vol.14 , Issue.2 , pp. 303-324
    • Dang, C.1    Xu, L.2
  • 7
    • 0032216898 scopus 로고    scopus 로고
    • The geometry of algorithms with orthogonality constraints
    • Edelman, A., Arias, T. A., Smith, S. T.: The geometry of algorithms with orthogonality constraints. SIAM J. Matrix Anal. Appl. 20, 303-353 (1998)
    • (1998) SIAM J. Matrix Anal. Appl. , vol.20 , pp. 303-353
    • Edelman, A.1    Arias, T.A.2    Smith, S.T.3
  • 8
    • 0021432552 scopus 로고
    • A graph distance measure for image analysis
    • Eshera, E., Fu, K. S.: A graph distance measure for image analysis. IEEE Trans. SMC 14 (3), 396-408 (1984)
    • (1984) IEEE Trans. SMC , vol.14 , Issue.3 , pp. 396-408
    • Eshera, E.1    Fu, K.S.2
  • 9
    • 0002834189 scopus 로고
    • Autoencoders, minimum description length and Helmholtz free energy
    • Hinton, G. E., Zemel, R. S.: Autoencoders, minimum description length and Helmholtz free energy. Adv. NIPS 6, 3-10 (1994)
    • (1994) Adv. NIPS , vol.6 , pp. 3-10
    • Hinton, G.E.1    Zemel, R.S.2
  • 10
    • 0021835689 scopus 로고
    • Neural computation of decisions in optimization problems
    • Hopfield, J. J., Tank, D. W.: Neural computation of decisions in optimization problems. Biol. Cybern. 52, 141-152 (1985)
    • (1985) Biol. Cybern , vol.52 , pp. 141-152
    • Hopfield, J.J.1    Tank, D.W.2
  • 12
    • 4043084564 scopus 로고    scopus 로고
    • Tutoiral on variational approximation methods
    • Opper, M., Saad, D. eds., MIT press
    • Jaakkola, T. S.: Tutoiral on variational approximation methods. In: Opper, M., Saad, D. (eds.) Advanced Mean Field Methods: Theory and Pratice, pp. 129-160. MIT press (2001)
    • (2001) Advanced Mean Field Methods: Theory and Pratice , pp. 129-160
    • Jaakkola, T.S.1
  • 13
    • 0033225865 scopus 로고    scopus 로고
    • Introduction to variational methods for graphical models
    • Jordan, M., Ghahramani, Z., Jaakkola, T., Saul, L.: Introduction to variational methods for graphical models. Mach. Learn. 37, 183-233 (1999)
    • (1999) Mach. Learn , vol.37 , pp. 183-233
    • Jordan, M.1    Ghahramani, Z.2    Jaakkola, T.3    Saul, L.4
  • 15
    • 26444479778 scopus 로고
    • Optimization by simulated annealing
    • Kirkpatrick, S., Gelatt, C. G. Jr., Vecchi, M. P.: Optimization by simulated annealing. Science 220, 671-680 (1983)
    • (1983) Science , vol.220 , pp. 671-680
    • Kirkpatrick, S.1    Gelatt, C.G.J.2    Vecchi, M.P.3
  • 17
  • 18
    • 0030676410 scopus 로고    scopus 로고
    • Maximum likelihood for blind separation and deconvolution of noisy signals using mixture models
    • Moulines, E., Cardoso, J., Gassiat, E.: Maximum likelihood for blind separation and deconvolution of noisy signals using mixture models. Proc. ICASSP97, pp. 3617-3620 (1997)
    • (1997) Proc. ICASSP97 , pp. 3617-3620
    • Moulines, E.1    Cardoso, J.2    Gassiat, E.3
  • 19
    • 0002788893 scopus 로고    scopus 로고
    • A view of the EM algorithm that justifies incremental, sparse, and other variants
    • Jordan, M. I. ed., MIT Press, Cambridge, MA
    • Neal, R., Hinton, G. E.: A view of the EM algorithm that justifies incremental, sparse, and other variants. In: Jordan, M. I. (ed.) Learning in Graphical Models, pp. 355-368. MIT Press, Cambridge, MA (1999)
    • (1999) Learning in Graphical Models , pp. 355-368
    • Neal, R.1    Hinton, G.E.2
  • 20
    • 0031084370 scopus 로고    scopus 로고
    • Regression and time series model selection using variants of the schwarz information criterion
    • Neath, A. A., Cavanaugh, J. E.: Regression and time series model selection using variants of the schwarz information criterion. Commun. Stat. A 26, 559-580 (1997)
    • (1997) Commun. Stat. a , vol.26 , pp. 559-580
    • Neath, A.A.1    Cavanaugh, J.E.2
  • 21
    • 0025490985 scopus 로고
    • Networks for approximation and learning. Proc
    • Poggio, T., Girosi, F.: Networks for approximation and learning. Proc. IEEE 78, 1481-1497 (1990)
    • (1990) IEEE , vol.78 , pp. 1481-1497
    • Poggio, T.1    Girosi, F.2
  • 22
    • 77954759462 scopus 로고
    • Bayesian statistics: Principles, models, and applications
    • Press, S. J.: Bayesian statistics: principles, models, and applications. Factors. Wiley (1989)
    • (1989) Factors. Wiley
    • Press, S.J.1
  • 24
    • 0033561894 scopus 로고    scopus 로고
    • On cross validation for model selection
    • Rivals, I., Personnaz, L.: On cross validation for model selection. Neural Comput. 11, 863-870 (1999)
    • (1999) Neural Comput , vol.11 , pp. 863-870
    • Rivals, I.1    Personnaz, L.2
  • 26
    • 77954762302 scopus 로고    scopus 로고
    • Numerical Bayesian methods applied to signal processing
    • New York
    • Ruanaidh, O., Joseph, J. K.: Numerical Bayesian methods applied to signal processing. Springer-Verlag, New York (1996)
    • (1996) Springer-Verlag
    • Ruanaidh, O.1    Joseph, J.K.2
  • 28
    • 0000120766 scopus 로고
    • Estimating the dimension of a model
    • Schwarz, G.: Estimating the dimension of a model. Ann. Stat. 6, 461-464 (1978)
    • (1978) Ann. Stat , vol.6 , pp. 461-464
    • Schwarz, G.1
  • 29
    • 0000319198 scopus 로고
    • Cross-validation: A review
    • Stone, M.: Cross-validation: a review. Math. Operat. Stat. 9, 127-140 (1978)
    • (1978) Math. Operat. Stat , vol.9 , pp. 127-140
    • Stone, M.1
  • 31
    • 0024069925 scopus 로고
    • An eigendecomposition approach to weighted graph matching problems
    • Umeyama, S.: An eigendecomposition approach to weighted graph matching problems. IEEE Trans. Pattern Anal. Mach. Intell. 10 (5), 695-703 (1988)
    • (1988) IEEE Trans. Pattern Anal. Mach. Intell , vol.10 , Issue.5 , pp. 695-703
    • Umeyama, S.1
  • 32
    • 3042530277 scopus 로고
    • The Nature of Statistical Learning Theory
    • Vapnik, V. N.: The Nature of Statistical Learning Theory. Springer (1995)
    • (1995) Springer
    • Vapnik, V.N.1
  • 33
    • 0003969585 scopus 로고    scopus 로고
    • Estimation of Dependences Based on Empirical Data
    • Vapnik, V. N.: Estimation of Dependences Based on Empirical Data. Springer (2006)
    • (2006) Springer
    • Vapnik, V.N.1
  • 34
    • 0000107517 scopus 로고
    • An information measure for classification
    • Wallace, C. S., Boulton, D. M.: An information measure for classification. Comput. J. 11, 185-194 (1968)
    • (1968) Comput. J. , vol.11 , pp. 185-194
    • Wallace, C.S.1    Boulton, D.M.2
  • 35
    • 77954760297 scopus 로고    scopus 로고
    • Learning Gaussian mixture models by structural risk minimization
    • Wang, L., Feng, J.: Learning Gaussian mixture models by structural risk minimization. Proc. 2005
    • (2005) Proc.
    • Wang, L.1    Feng, J.2
  • 37
    • 0003217532 scopus 로고
    • Combinatorial optimization neural nets based on a hybrid of Lagrange and transformation approaches
    • World Congress Neural Networks, SanDiego, 1994
    • Xu, L.: Combinatorial optimization neural nets based on a hybrid of Lagrange and transformation approaches. Proc. 1994 World Congress Neural Networks, pp. 399-404. SanDiego (1994)
    • (1994) Proc. , pp. 399-404
    • Xu, L.1
  • 38
    • 0005906827 scopus 로고
    • Bayesian-Kullback coupled YING-YANG machines: Unified learnings and new results on vector quantization
    • Beijing
    • Xu, L.: Bayesian-Kullback coupled YING-YANG machines: unified learnings and new results on vector quantization. Proc. ICONIP95, pp. 977-988. Beijing (1995)
    • (1995) Proc. ICONIP95 , pp. 977-988
    • Xu, L.1
  • 39
    • 0141757082 scopus 로고
    • On the hybrid LT combinatorial optimization: New U-shape barrier, sigmoid activation, least leaking energy and maximum entropy
    • Beijing
    • Xu, L.: On the hybrid LT combinatorial optimization: new U-shape barrier, sigmoid activation, least leaking energy and maximum entropy. Proc. ICONIP'95, pp. 309-312. Beijing (1995)
    • (1995) Proc. ICONIP'95 , pp. 309-312
    • Xu, L.1
  • 40
    • 0006005149 scopus 로고    scopus 로고
    • Bayesian Ying-Yang system and theory as a unified statistical learning approach (I): Unsupervised and semi-unsupervised learning
    • Amari, K. ed., Springer-Verlag
    • Xu, L.: Bayesian Ying-Yang system and theory as a unified statistical learning approach (I): unsupervised and semi-unsupervised learning. In: Amari, K. (ed.) Brain-like Computing and Intelligent Information Systems, pp. 241-274. Springer-Verlag (1997)
    • (1997) Brain-like Computing and Intelligent Information Systems , pp. 241-274
    • Xu, L.1
  • 41
    • 0035391741 scopus 로고    scopus 로고
    • BYY harmony learning, independent state space, and generalized APT financial analyses
    • DOI 10.1109/72.935094, PII S1045922701050135
    • Xu, L.: BYY harmony learning, independent state space and generalized APT financial analyses. IEEE Trans. Neural Netw. 12, 822-849 (2001) (Pubitemid 32732823)
    • (2001) IEEE Transactions on Neural Networks , vol.12 , Issue.4 , pp. 822-849
    • Xu, L.1
  • 42
    • 0141633856 scopus 로고    scopus 로고
    • Distribution approximation, combinatorial optimization, and Lagrange-barrier
    • July 20-24, Portland 2003
    • Xu, L.: Distribution approximation, combinatorial optimization, and Lagrange-barrier. Proc. Intl. Joint Conf. on Neural Networks 2003, July 20-24, pp. 2354-2359. Portland (2003)
    • (2003) Proc. Intl. Joint Conf. on Neural Networks , pp. 2354-2359
    • Xu, L.1
  • 43
    • 3843095548 scopus 로고    scopus 로고
    • Independent component analysis and extensions with noise and time
    • Neural Inf. Process. Lett. Rev
    • Xu, L.: Independent component analysis and extensions with noise and time: A Bayesian Ying-Yang learning perspective. Neural Inf. Process. Lett. Rev. 1, 1-52 (2003)
    • (2003) A Bayesian Ying-Yang Learning Perspective , vol.1 , pp. 1-52
    • Xu, L.1
  • 44
    • 3843066216 scopus 로고    scopus 로고
    • Temporal BYY encoding, Markovian state spaces, and space dimension determination
    • Xu, L.: Temporal BYY encoding, Markovian state spaces, and space dimension determination. IEEE Trans. Neural Netw. 15, 1276-1295 (2004)
    • (2004) IEEE Trans. Neural Netw , vol.15 , pp. 1276-1295
    • Xu, L.1
  • 45
    • 3843136240 scopus 로고    scopus 로고
    • Advances on BYY harmony learning: Information theoretic perspective, generalized projection geometry, and independent factor auto-determination
    • Xu, L.: Advances on BYY harmony learning: information theoretic perspective, generalized projection geometry, and independent factor auto-determination. IEEE Trans. Neural Netw. 15, 885-902 (2004)
    • (2004) IEEE Trans. Neural Netw , vol.15 , pp. 885-902
    • Xu, L.1
  • 46
    • 3843056324 scopus 로고    scopus 로고
    • Bayesian Ying Yang learning φ (I): A unified perspective for statistical modeling
    • Zhong, L. ed., Springer
    • Xu, L.: Bayesian Ying Yang learning φ (I): a unified perspective for statistical modeling. In: Zhong, L. (ed.) Intelligent Technologies for Information analysis, pp. 615-659. Springer (2004)
    • (2004) Intelligent Technologies for Information Analysis , pp. 615-659
    • Xu, L.1
  • 47
    • 24944561673 scopus 로고    scopus 로고
    • One-Bit-Matching ICA Theorem, convex-concave programming, and combinatorial optimization. Lecture Notes in Computer Science
    • Springer-Verlag
    • Xu, L.: One-Bit-Matching ICA Theorem, convex-concave programming, and combinatorial optimization. Lecture Notes in Computer Science, Advances in Neural Networks, vol. 3496, pp. 5-20. Springer-Verlag (2005)
    • (2005) Advances in Neural Networks , vol.3496 , pp. 5-20
    • Xu, L.1
  • 48
    • 33847287742 scopus 로고    scopus 로고
    • One-Bit-Matching theorem for ICA, convex-concave programming on polyhedral set, and distribution approximation for combinatorics
    • Xu, L.: One-Bit-Matching theorem for ICA, convex-concave programming on polyhedral set, and distribution approximation for combinatorics. Neural Comput. 19, 546-569 (2007)
    • (2007) Neural Comput , vol.19 , pp. 546-569
    • Xu, L.1
  • 49
    • 34249982553 scopus 로고    scopus 로고
    • A trend onregularization and model selection in statistical learning: A Bayesian Ying Yang learning perspective
    • Duch, M. ed., Springer-Verlag
    • Xu, L.: A trend onregularization and model selection in statistical learning: A Bayesian Ying Yang learning perspective. In: Duch, M. (ed.) Challenges for Computational Intelligence, pp. 365-406. Springer-Verlag (2007)
    • (2007) Challenges for Computational Intelligence , pp. 365-406
    • Xu, L.1
  • 50
    • 34247105235 scopus 로고    scopus 로고
    • A unified perspective and new results on RHT computing, mixture based learning, and multilearner based problem solving
    • Xu, L.: A unified perspective and new results on RHT computing, mixture based learning, and multilearner based problem solving. Pattern Recognit. 40, 2129-2153 (2007)
    • (2007) Pattern Recognit , vol.40 , pp. 2129-2153
    • Xu, L.1
  • 51
    • 46049106446 scopus 로고    scopus 로고
    • Bayesian Ying Yang learning
    • Xu, L.: Bayesian Ying Yang learning. Scholarpedia 2 (3), 1809 (2007). http://scholarpedia.org/article/BayesianYingYangLearning
    • (2007) Scholarpedia , vol.2 , Issue.3 , pp. 1809
    • Xu, L.1
  • 54
    • 2342533082 scopus 로고    scopus 로고
    • On convergence properties of the EM algorithm for Gaussian mixtures
    • Xu, L., Jordan, M. I.: On convergence properties of the EM algorithm for Gaussian mixtures. Neural Comput. 8 (1), 129-151 (1996)
    • (1996) Neural Comput , vol.8 , Issue.1 , pp. 129-151
    • Xu, L.1    Jordan, M.I.2
  • 55
    • 0035482004 scopus 로고    scopus 로고
    • A PCA approach for fast retrieval of structural patterns in attributed graphs
    • Xu, L., King, I.: A PCA approach for fast retrieval of structural patterns in attributed graphs. IEEE Trans. Syst. Man Cybernet. B 31 (5), 812-817 (2001)
    • (2001) IEEE Trans. Syst. Man Cybernet. B , vol.31 , Issue.5 , pp. 812-817
    • Xu, L.1    King, I.2
  • 56
    • 0027867610 scopus 로고
    • A PCA like rule for pattern classification based on attributed graph
    • Oct, Nagoya, Japan 1993
    • Xu, L., Klasa, S.: A PCA like rule for pattern classification based on attributed graph. Proc. 1993 Intl. Joint Conf. on Neural Networks, Oct. 1993, pp. 1281-1284. Nagoya, Japan (1993)
    • (1993) Proc. 1993 Intl. Joint Conf. on Neural Networks , pp. 1281-1284
    • Xu, L.1    Klasa, S.2
  • 57
    • 0027629412 scopus 로고    scopus 로고
    • Rival penalized competitive learning for clustering analysis, RBF net and curve detection
    • Xu, L., Krzyzak, A., Oja, E.: Rival penalized competitive learning for clustering analysis, RBF net and curve detection. IEEE Trans. on Neural Netw. 4, 636-649.
    • IEEE Trans. on Neural Netw , vol.4 , pp. 636-649
    • Xu, L.1    Krzyzak, A.2    Oja, E.3
  • 59
    • 46049083679 scopus 로고    scopus 로고
    • Rival penalized competitive learning
    • Retried from
    • XU, L.: Rival penalized competitive learning. Scholarpedia 2 (8), 1810 Retried from http://www.scholarpedia.org/article/Rival-penalized-competitive- learning
    • Scholarpedia , vol.2 , Issue.8 , pp. 1810
    • Xu, L.1


* 이 정보는 Elsevier사의 SCOPUS DB에서 KISTI가 분석하여 추출한 것입니다.