Bayesian posterior sampling via stochastic gradient fisher scoring

Proceedings of the 29th International Conference on Machine Learning, ICML 2012

Volumn 2, Issue , 2012, Pages 1591-1598

  Ahn, Sungjin ^a   Korattikara, Anoop ^a   Welling, Max ^a  

^a Ringgold Standard Institution Informatics   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

BURN-IN; CENTRAL LIMIT THEOREM; LANGEVIN EQUATION; MIXING RATES; NORMAL APPROXIMATION; OPTIMIZERS; POSTERIOR DISTRIBUTIONS; STOCHASTIC GRADIENT;

APPROXIMATION ALGORITHMS; DIFFERENTIAL EQUATIONS; LEARNING SYSTEMS; MIXING;

COMMUNICATION CHANNELS (INFORMATION THEORY);

EID: 84867125855     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (11)

1. Andrieu, C. and Thorns, J. A tutorial on adaptive mcmc. Statistics and Computing, 18(4):343-373, 2009.
2. Borkar, V.S. Stochastic approximation with two time scales. Systems and Control Letters, 29(5):291-294, 1997.
3. Bottou, L. and Bousquet, O. The tradeoffs of large scale learning. In Advances in Neural Information Processing Systems, volume 20, pp. 161-168, 2008.
4. Girolami, M. and Calderhead, B. Riemann manifold langevin and hamiltonian monte carlo. Journal of the Royal Statistical Society B, 73(2):1-37, 2010.
5. th International Conference on Machine learning, pp. 536-543. ACM, 2008.
6. Le Cam, L.M. Asymptotic methods in statistical decision theory. Springer, 1986.
7. Neal, R.M. Probabilistic inference using markov chain monte carlo methods. Technical Report CRG-TR-93-1, University of Toronto, Computer Science, 1993.
8. th Intl. Conf. Artificial Intelligence and Statistics (AIstats), pp. 436-443, San Juan, Puerto Rico, 2007.
9. Scott, W.A. Maximum likelihood estimation using the empirical fisher information matrix. Journal of Statistical Computation and Simulation, 72(8):599-611, 2002.
10. Seeger, M. Low rank updates for the cholesky decomposition. Technical report, University of California Berkeley, 2004. URL http://lapma1.epfl.ch/ papers/cholupdate.shtml.
11. Welling, M. and Teh, Y.W. Bayesian learning via stochastic gradient langevin dynamics. In Proceedings of the 28th International Conference on Machine Learning (ICML), pp. 681-688, 2011.