Black-Box α-divergence minimization

33rd International Conference on Machine Learning, ICML 2016

Volumn 4, Issue , 2016, Pages 2256-2273

  Hernández Lobato, José Miguel ^a   Li, Yingzhen ^b   Rowland, Mark ^b   Hernández Lobato, Daniel ^c   Bui, Thang D ^b   Ttarner, Richard E ^b  

^a HARVARD UNIVERSITY   (United States)

^b UNIVERSITY OF CAMBRIDGE   (United Kingdom)

^c UNIVERSIDAD AUTÓNOMA DE MADRID   (Spain)

Author keywords

[No Author keywords available]

Indexed keywords

ARTIFICIAL INTELLIGENCE; BARIUM COMPOUNDS; STOCHASTIC SYSTEMS;

APPROXIMATE INFERENCE; AUTOMATIC DIFFERENTIATIONS; EXPECTATION PROPAGATION; LIKELIHOOD FUNCTIONS; PROBABILISTIC MODELS; STANDARD SETTING; STOCHASTIC GRADIENT DESCENT; VARIATIONAL BAYES;

LEARNING SYSTEMS;

EID: 84998694412     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (4)

1. [Hernandez-Lobato and Adams, 2015] Hernandez-Lobato, J. M. and Adams, R. (2015). Probabilistic back- propagation for scalable learning of Bayesian neural networks. In Proceedings of the 32nd International Conference on Machine Learning, ICML 2015, Lille, France, 6-11 July 2015, pages 1861-1869.
2. [Heskes and Zoeter, 2002] Heskes, T. and Zoeter, O. (2002). Expectation propagation for approximate inference in dynamic Bayesian networks. In Proceedings of the Eighteenth conference on Uncertainty in artificial intelligence, pages 216-223. Morgan Kaufmann Publishers Inc.
3. [Minka, 2001] Minka, T. P. (2001). Expectation propagation for approximate Bayesian inference. In Proceedings of the Seventeenth conference on Uncertainty in artificial intelligence, pages 362-369. Morgan Kaufmann Publishers Inc.
4. [Opper and Winther, 2005] Opper, M. and Winther, O. (2005). Expectation consistent approximate inference. The Journal of Machine Learning Research, 6:2177-2204.