Variational Generative Stochastic Networks with Collaborative Shaping

Philip Bachman, Doina Precup
2015 International Conference on Machine Learning  
We develop an approach to training generative models based on unrolling a variational autoencoder into a Markov chain, and shaping the chain's trajectories using a technique inspired by recent work in Approximate Bayesian computation. We show that the global minimizer of the resulting objective is achieved when the generative model reproduces the target distribution. To allow finer control over the behavior of the models, we add a regularization term inspired by techniques used for regularizing
more » ... certain types of policy search in reinforcement learning. We present empirical results on the MNIST and TFD datasets which show that our approach offers state-of-the-art performance, both quantitatively and from a qualitative point of view.
dblp:conf/icml/BachmanP15 fatcat:pyq33sdwdncilo7k5msdn7da5a