Variational inference for Monte Carlo objectives

02/22/2016
by   Andriy Mnih, et al.
0

Recent progress in deep latent variable models has largely been driven by the development of flexible and scalable variational inference methods. Variational training of this type involves maximizing a lower bound on the log-likelihood, using samples from the variational posterior to compute the required gradients. Recently, Burda et al. (2016) have derived a tighter lower bound using a multi-sample importance sampling estimate of the likelihood and showed that optimizing it yields models that use more of their capacity and achieve higher likelihoods. This development showed the importance of such multi-sample objectives and explained the success of several related approaches. We extend the multi-sample approach to discrete latent variables and analyze the difficulty encountered when estimating the gradients involved. We then develop the first unbiased gradient estimator designed for importance-sampled objectives and evaluate it at training generative and structured output prediction models. The resulting estimator, which is based on low-variance per-sample learning signals, is both simpler and more effective than the NVIL estimator proposed for the single-sample variational objective, and is competitive with the currently used biased estimators.

READ FULL TEXT
research
10/09/2018

Doubly Reparameterized Gradient Estimators for Monte Carlo Objectives

Deep latent variable models have become a popular model choice due to th...
research
09/12/2018

Discretely Relaxing Continuous Variables for tractable Variational Inference

We explore a new research direction in Bayesian variational inference wi...
research
07/24/2019

On importance-weighted autoencoders

The importance weighted autoencoder (IWAE) (Burda et al., 2016) is a pop...
research
07/24/2019

On the relationship between variational inference and adaptive importance sampling

The importance weighted autoencoder (IWAE) (Burda et al., 2016) and rewe...
research
05/31/2021

A unified view of likelihood ratio and reparameterization gradients

Reparameterization (RP) and likelihood ratio (LR) gradient estimators ar...
research
05/28/2021

ARMS: Antithetic-REINFORCE-Multi-Sample Gradient for Binary Variables

Estimating the gradients for binary variables is a task that arises freq...
research
06/18/2020

DisARM: An Antithetic Gradient Estimator for Binary Latent Variables

Training models with discrete latent variables is challenging due to the...

Please sign up or login with your details

Forgot password? Click here to reset