Learning to Draw Samples: With Application to Amortized MLE for Generative Adversarial Learning

Abstract

We propose a simple algorithm to train stochastic neural networks to draw samples from given target distributions for probabilistic inference. Our method is based on iteratively adjusting the neural network parameters so that the output changes along a Stein variational gradient that maximumly decreases the KL divergence with the target distribution. Our method works for any target distribution specified by their unnormalized density function, and can train any black-box architectures that are differentiable in terms of the parameters we want to adapt. As an application of our method, we propose an amortized MLE algorithm for training deep energy model, where a neural sampler is adaptively trained to approximate the likelihood function. Our method mimics an adversarial game between the deep energy model and the neural sampler, and obtains realistic-looking images competitive with the state-of-the-art results.

Under review as a conference paper at ICLR 2017

References in corpus (1)

• Energy-based Generative Adversarial Network

Cited by in corpus (7)

• Adversarial Feature Matching for Text Generation
• Boosting Deep Learning Risk Prediction with Generative Adversarial Networks for Electronic Health Records
• Riemannian Stein Variational Gradient Descent for Bayesian Inference
• Learning Model Reparametrizations: Implicit Variational Inference by Fitting MCMC distributions
• Towards Robust, Locally Linear Deep Networks
• Learning Deep Energy Models: Contrastive Divergence vs. Amortized MLE
• Stochastic Maximum Likelihood Optimization via Hypernetworks