Fast Gradient-Based Inference with Continuous Latent Variable Models in Auxiliary Form

Abstract

We propose a technique for increasing the efficiency of gradient-based inference and learning in Bayesian networks with multiple layers of continuous latent vari- ables. We show that, in many cases, it is possible to express such models in an auxiliary form, where continuous latent variables are conditionally deterministic given their parents and a set of independent auxiliary variables. Variables of mod- els in this auxiliary form have much larger Markov blankets, leading to significant speedups in gradient-based inference, e.g. rapid mixing Hybrid Monte Carlo and efficient gradient-based optimization. The relative efficiency is confirmed in ex- periments.

References in corpus (1)

• Expectation Propagation for approximate Bayesian inference

Cited by in corpus (10)

• NIPS 2016 Tutorial: Generative Adversarial Networks
• Adversarially Learned Inference
• Variational Dropout and the Local Reparameterization Trick
• Deep Generative Stochastic Networks Trainable by Backprop
• Efficient Gradient-Based Inference through Transformations between Bayes Nets and Neural Nets
• Energy-based Models for Video Anomaly Detection
• Local Clustering with Mean Teacher for Semi-supervised Learning
• GSNs : Generative Stochastic Networks
• Convex Smoothed Autoencoder-Optimal Transport model
• Cross-Domain Latent Modulation for Variational Transfer Learning