Skip to yearly menu bar Skip to main content


Spotlight

Training Discrete Deep Generative Models via Gapped Straight-Through Estimator

Ting-Han Fan · Ta-Chung Chi · Alexander Rudnicky · Peter Ramadge

Ballroom 1 & 2

Abstract:

While deep generative models have succeeded in image processing, natural language processing, and reinforcement learning, training that involves discrete random variables remains challenging due to the high variance of its gradient estimation process. Monte Carlo is a common solution used in most variance reduction approaches. However, this involves time-consuming resampling and multiple function evaluations. We propose a Gapped Straight-Through (GST) estimator to reduce the variance without incurring resampling overhead. This estimator is inspired by the essential properties of Straight-Through Gumbel-Softmax. We determine these properties and show via an ablation study that they are essential. Experiments demonstrate that the proposed GST estimator enjoys better performance compared to strong baselines on two discrete deep generative modeling tasks, MNIST-VAE and ListOps.

Chat is not available.