메뉴 건너뛰기




Volumn 7, Issue , 2006, Pages 1743-1788

Learning factor graphs in polynomial time and sample complexity

Author keywords

Bayesian networks; Factor graphs; Markov networks; Parameter and structure learning; Probabilistic graphical models

Indexed keywords

ALGORITHMS; COMPUTATIONAL COMPLEXITY; MARKOV PROCESSES; MAXIMUM LIKELIHOOD ESTIMATION; PARAMETER ESTIMATION; POLYNOMIAL APPROXIMATION; SAMPLING;

EID: 33747670266     PISSN: 15337928     EISSN: 15337928     Source Type: Journal    
DOI: None     Document Type: Article
Times cited : (138)

References (41)
  • 1
    • 80053202166 scopus 로고    scopus 로고
    • Learning factor graphs in polynomial time & sample complexity
    • P. Abbeel, D. Koller, and A. Y. Ng. Learning factor graphs in polynomial time & sample complexity. In Proc. UAI, 2005.
    • (2005) Proc. UAI
    • Abbeel, P.1    Koller, D.2    Ng, A.Y.3
  • 2
    • 0005809110 scopus 로고
    • Polynomial learnability of probabilistic concepts with respect to the Kullback-Leibler divergence
    • N. Abe, J. Takeuchi, and M. Warmuth. Polynomial learnability of probabilistic concepts with respect to the Kullback-Leibler divergence. In Proc. COLT, 1991.
    • (1991) Proc. COLT
    • Abe, N.1    Takeuchi, J.2    Warmuth, M.3
  • 3
    • 0001841122 scopus 로고
    • On the computational complexity of approximating probability distributions by probabilistic automata
    • N. Abe, J. Takeuchi, and M. Warmuth. On the computational complexity of approximating probability distributions by probabilistic automata. Machine Learning, 1992.
    • (1992) Machine Learning
    • Abe, N.1    Takeuchi, J.2    Warmuth, M.3
  • 4
  • 5
    • 0001051761 scopus 로고
    • On the computational complexity of Ising spin glass models
    • F. Barahona. On the computational complexity of Ising spin glass models. J. Phys. A, 1982.
    • (1982) J. Phys. A
    • Barahona, F.1
  • 6
    • 33747669639 scopus 로고
    • Efficiency of pseudo-likelihood estimation for simple Gaussian fields
    • J. Besag. Efficiency of pseudo-likelihood estimation for simple Gaussian fields. Biometrika, 1974a.
    • (1974) Biometrika
    • Besag, J.1
  • 9
    • 0001019707 scopus 로고    scopus 로고
    • Learning Bayesian networks is NP-complete
    • D. Fisher and H.J. Lenz, editors, Springer-Verlag
    • D. M. Chickering. Learning Bayesian networks is NP-Complete. In D. Fisher and H.J. Lenz, editors, Learning from Data: Artificial Intelligence and Statistics V, pages 121-130. Springer-Verlag, 1996.
    • (1996) Learning from Data: Artificial Intelligence and Statistics V , pp. 121-130
    • Chickering, D.M.1
  • 10
    • 0038517651 scopus 로고    scopus 로고
    • Finding optimal Bayesian networks
    • D. M. Chickering and C. Meek. Finding optimal Bayesian networks. In Proc. UAI, 2002.
    • (2002) Proc. UAI
    • Chickering, D.M.1    Meek, C.2
  • 11
    • 33747736365 scopus 로고    scopus 로고
    • Large-sample learning of Bayesian networks is hard
    • D. M. Chickering, C. Meek, and D. Heckerman. Large-sample learning of Bayesian networks is hard. In Proc. UAI, 2003.
    • (2003) Proc. UAI
    • Chickering, D.M.1    Meek, C.2    Heckerman, D.3
  • 12
  • 13
    • 0000695777 scopus 로고
    • On consistency of a class of estimators for exponential families of Markov random fields on the lattice
    • F. Comets. On consistency of a class of estimators for exponential families of Markov random fields on the lattice. Annals of Statistics, 1992.
    • (1992) Annals of Statistics
    • Comets, F.1
  • 16
    • 0031269467 scopus 로고    scopus 로고
    • The sample complexity of learning fixed structure Bayesian networks
    • S. Dasgupta. The sample complexity of learning fixed structure Bayesian networks. Machine Learning, 1997.
    • (1997) Machine Learning
    • Dasgupta, S.1
  • 17
    • 0012135466 scopus 로고    scopus 로고
    • Learning polytrees
    • S. Dasgupta. Learning polytrees. In Proc. UAI, 1999.
    • (1999) Proc. UAI
    • Dasgupta, S.1
  • 19
    • 0011582345 scopus 로고    scopus 로고
    • Efficient stepwise selection in decomposable models
    • Morgan Kaufmann Publishers Inc. ISBN 1-55860-800-1
    • A. Deshpande, M. N. Garofalakis, and M. I. Jordan. Efficient stepwise selection in decomposable models. In Proc. UAI, pages 128-135. Morgan Kaufmann Publishers Inc., 2001. ISBN 1-55860-800-1.
    • (2001) Proc. UAI , pp. 128-135
    • Deshpande, A.1    Garofalakis, M.N.2    Jordan, M.I.3
  • 20
    • 0000319413 scopus 로고    scopus 로고
    • On the sample complexity of learning Bayesian networks
    • N. Friedman and Z. Yakhini. On the sample complexity of learning Bayesian networks. In Proc. UAI, 1996.
    • (1996) Proc. UAI
    • Friedman, N.1    Yakhini, Z.2
  • 23
    • 0009856498 scopus 로고
    • Consistency of maximum likelihood and pseudo-likelihood estimators for Gibbsian distributions
    • W. Fleming and P.-L. Lions, editors. Springer, New York
    • B. Gidas. Consistency of maximum likelihood and pseudo-likelihood estimators for Gibbsian distributions. In W. Fleming and P.-L. Lions, editors, Stochastic differential systems, stochastic control theory and applications. Springer, New York, 1988.
    • (1988) Stochastic Differential Systems, Stochastic Control Theory and Applications
    • Gidas, B.1
  • 26
    • 33747644284 scopus 로고
    • Learning and robust learning of product distributions
    • K. L. Höffgen. Learning and robust learning of product distributions. In Proc. COLT, 1993.
    • (1993) Proc. COLT
    • Höffgen, K.L.1
  • 28
    • 0027677367 scopus 로고
    • Polynomial-time approximation algorithms for the Ising model
    • M. Jerrum and A. Sinclair. Polynomial-time approximation algorithms for the Ising model. SIAM J. Comput., 1993.
    • (1993) SIAM J. Comput.
    • Jerrum, M.1    Sinclair, A.2
  • 29
    • 0030509462 scopus 로고    scopus 로고
    • A consistent model selection procedure for Markov random fields based on penalized pseudolikelihood
    • C. Ji and L. Seymour. A consistent model selection procedure for Markov random fields based on penalized pseudolikelihood. Annals of Applied Probability, 1996.
    • (1996) Annals of Applied Probability
    • Ji, C.1    Seymour, L.2
  • 30
    • 64049102502 scopus 로고    scopus 로고
    • Learning Markov networks: Maximum bounded tree-width graphs
    • D. Karger and N. Srebro. Learning Markov networks: maximum bounded tree-width graphs. In Symposium on Discrete Algorithms, pages 392-401, 2001.
    • (2001) Symposium on Discrete Algorithms , pp. 392-401
    • Karger, D.1    Srebro, N.2
  • 35
    • 10244268660 scopus 로고    scopus 로고
    • Efficiently inducing features of conditional random fields
    • A. McCallum. Efficiently inducing features of conditional random fields. In Proc. UAI, 2003.
    • (2003) Proc. UAI
    • McCallum, A.1
  • 37
    • 60649090124 scopus 로고    scopus 로고
    • PAC-learning bounded tree-width graphical models
    • M. Narasimhan and J. Bilmes. PAC-learning bounded tree-width graphical models. In Proc. UAI, 2004.
    • (2004) Proc. UAI
    • Narasimhan, M.1    Bilmes, J.2
  • 38
    • 59549087165 scopus 로고    scopus 로고
    • On discriminative vs. generative classifiers: A comparison of logistic regression and naive Bayes
    • A. Y. Ng and M. I. Jordan. On discriminative vs. generative classifiers: A comparison of logistic regression and naive Bayes. In NIPS 14, 2002.
    • (2002) NIPS 14
    • Ng, A.Y.1    Jordan, M.I.2
  • 41
    • 0004031805 scopus 로고    scopus 로고
    • Understanding belief propagation and its generalizations
    • Mitsubishi Electric Reseach Laboratories
    • J. S. Yedidia, W. T. Freeman, and Y. Weiss. Understanding belief propagation and its generalizations. Technical report, Mitsubishi Electric Reseach Laboratories, 2001.
    • (2001) Technical Report
    • Yedidia, J.S.1    Freeman, W.T.2    Weiss, Y.3


* 이 정보는 Elsevier사의 SCOPUS DB에서 KISTI가 분석하여 추출한 것입니다.