DeepAI
Log In Sign Up

Recursive Inference for Variational Autoencoders

11/17/2020
by   Minyoung Kim, et al.
0

Inference networks of traditional Variational Autoencoders (VAEs) are typically amortized, resulting in relatively inaccurate posterior approximation compared to instance-wise variational optimization. Recent semi-amortized approaches were proposed to address this drawback; however, their iterative gradient update procedures can be computationally demanding. To address these issues, in this paper we introduce an accurate amortized inference algorithm. We propose a novel recursive mixture estimation algorithm for VAEs that iteratively augments the current mixture with new components so as to maximally reduce the divergence between the variational and the true posteriors. Using the functional gradient approach, we devise an intuitive learning criteria for selecting a new mixture component: the new component has to improve the data likelihood (lower bound) and, at the same time, be as divergent from the current mixture distribution as possible, thus increasing representational diversity. Compared to recently proposed boosted variational inference (BVI), our method relies on amortized inference in contrast to BVI's non-amortized single optimization instance. A crucial benefit of our approach is that the inference at test time requires a single feed-forward pass through the mixture inference network, making it significantly faster than the semi-amortized approaches. We show that our approach yields higher test data likelihood than the state-of-the-art on several benchmark datasets.

READ FULL TEXT

page 1

page 2

page 3

page 4

02/05/2021

Reducing the Amortization Gap in Variational Autoencoders: A Bayesian Random Function Approach

Variational autoencoder (VAE) is a very successful generative model whos...
10/05/2018

Doubly Semi-Implicit Variational Inference

We extend the existing framework of semi-implicit variational inference ...
09/30/2019

Tightening Bounds for Variational Inference by Revisiting Perturbation Theory

Variational inference has become one of the most widely used methods in ...
11/20/2017

Likelihood Almost Free Inference Networks

Variational inference for latent variable models is prevalent in various...
01/10/2018

Inference Suboptimality in Variational Autoencoders

Amortized inference has led to efficient approximate inference for large...
07/05/2018

Learning in Variational Autoencoders with Kullback-Leibler and Renyi Integral Bounds

In this paper we propose two novel bounds for the log-likelihood based o...
11/06/2017

Fast amortized inference of neural activity from calcium imaging data with variational autoencoders

Calcium imaging permits optical measurement of neural activity. Since in...