Kernel Implicit Variational Inference

Abstract

Recent progress in variational inference has paid much attention to the flexibility of variational posteriors. One promising direction is to use implicit distributions, i.e., distributions without tractable densities as the variational posterior. However, existing methods on implicit posteriors still face challenges of noisy estimation and computational infeasibility when applied to models with high-dimensional latent variables. In this paper, we present a new approach named Kernel Implicit Variational Inference that addresses these challenges. As far as we know, for the first time implicit variational inference is successfully applied to Bayesian neural networks, which shows promising results on both regression and classification tasks.

Published as a conference paper at ICLR 2018

References in corpus (10)

• Weight Uncertainty in Neural Networks
• Learning in Implicit Generative Models
• Hierarchical Implicit Models and Likelihood-Free Variational Inference
• Improving Variational Auto-Encoders using Householder Flow
• A-NICE-MC: Adversarial Training for MCMC
• Variational Inference using Implicit Distributions
• Gradient Estimators for Implicit Models
• ZhuSuan: A Library for Bayesian Deep Learning
• Approximate Inference with Amortised MCMC
• Overpruning in Variational Bayesian Neural Networks

Cited by in corpus (5)

• The Functional Neural Process
• Semi-Implicit Variational Inference
• Latent Variable Modelling with Hyperbolic Normalizing Flows
• Doubly Semi-Implicit Variational Inference
• Stochastic Bayesian Neural Networks