Lecture 5

Readings:

Bayesian Learning via Stochastic Gradient Langevin Dynamics Links to an external site. Max Welling and Yee Whye Teh, ICML, 2011.

 

Stochastic Gradient Hamiltonian Monte Carlo Links to an external site. Tianqi Chen, Emily B. Fox, Carlos Guestrin, Journal of Machine Learning Research, 2014.

Download Slides

by Yanrong Li

 

Parallel Tempering for Training of Restricted Boltzmann Machines Links to an external site. Guillaume Desjardins, Aaron Courville, Yoshua Bengio, Pascal Vincent, Olivier Delalleau, Journal of Machine Learning Research, 2010.

 

See Also:

Preconditioned Stochastic Gradient Langevin Dynamics for Deep Neural Networks Links to an external site., Chunyuan Li, Changyou Chen, David Carlson and Lawrence Carin, AAAI 2016

 

Neural Adaptive Sequential Monte Carlo Links to an external site., Shixiang Gu, Zoubin Ghahramani, Richard E. Turner, arXiv 1506.03338, 2015

 

This article has an excellent survey of work on parallel MCMC methods:

Orthogonal parallel MCMC methods for sampling and optimization Links to an external site. L. Martino, V. Elviray, D. Luengoz, J. Corander, F. Louzada, arXiv 1507.08577, 2015