Markov Chain Monte Carlo and Variational Inference: Bridging the Gap

Recent advances in stochastic gradient variational inference have made it possible to perform variational Bayesian inference with posterior approximations containing auxiliary random variables. This enables us to explore a new synthesis of variational inference and Monte Carlo methods where we incorporate one or more steps of MCMC into our variational approximation. By doing so we obtain a rich class of inference algorithms bridging the gap between variational methods and MCMC, and offering the best of both worlds: fast posterior approximation through the maximization of an explicit objective, with the option of trading off additional computation for additional accuracy. We describe the theoretical foundations that make this possible and show some promising first results.

[1]  S. Adler.  Over-relaxation method for the Monte Carlo evaluation of the partition function for multiquadratic actions , 1981 .

[2]  Geoffrey E. Hinton,et al.  Autoencoders, Minimum Description Length and Helmholtz Free Energy , 1993, NIPS.

[3]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[4]  Jim Albert,et al.  Bayesian Computation with R , 2008 .

[5]  Radford M. Neal.  MCMC Using Hamiltonian Dynamics , 2011, 1206.1901.

[6]  Razvan Pascanu,et al.  Theano: new features and speed improvements , 2012, ArXiv.

[7]  Radford M. Neal.  How to View an MCMC Simulation as a Permutation, with Applications to Parallel Simulation and Improved Importance Sampling , 2012, 1205.0070.

[8]  Michael I. Jordan,et al.  Variational Bayesian Inference with Stochastic Search , 2012, ICML.

[9]  Tim Salimans,et al.  Fixed-Form Variational Posterior Approximation through Stochastic Linear Regression , 2012, ArXiv.

[10]  Karol Gregor,et al.  Neural Variational Inference and Learning in Belief Networks , 2014, ICML.

[11]  Daan Wierstra,et al.  Stochastic Backpropagation and Approximate Inference in Deep Generative Models , 2014, ICML.

[12]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[13]  Sean Gerrish,et al.  Black Box Variational Inference , 2013, AISTATS.

[14]  Hugo Larochelle,et al.  A Deep and Tractable Density Estimator , 2013, ICML.

[15]  Alex Graves,et al.  DRAW: A Recurrent Neural Network For Image Generation , 2015, ICML.

[16]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[17]  Thomas Brox,et al.  Learning to generate chairs with convolutional neural networks , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[18]  Thomas Brox,et al.  Learning to Generate Chairs, Tables and Cars with Convolutional Networks , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.