Tighter Variational Bounds are Not Necessarily Better
Abstract
We provide theoretical and empirical evidence that using tighter evidence lower bounds (ELBOs) can be detrimental to the process of learning an inference network by reducing the signal-to-noise ratio of the gradient estimator. Our results call into question common implicit assumptions that tighter ELBOs are better variational objectives for simultaneous model learning and inference amortization schemes. Based on our insights, we introduce three new algorithms: the partially importance weighted auto-encoder (PIWAE), the multiply importance weighted auto-encoder (MIWAE), and the combination importance weighted auto-encoder (CIWAE), each of which includes the standard importance weighted auto-encoder (IWAE) as a special case. We show that each can deliver improvements over IWAE, even when performance is measured by the IWAE target itself. Furthermore, our results suggest that PIWAE may be able to deliver simultaneous improvements in the training of both the inference and generative networks.
Cite
@article{arxiv.1802.04537,
title = {Tighter Variational Bounds are Not Necessarily Better},
author = {Tom Rainforth and Adam R. Kosiorek and Tuan Anh Le and Chris J. Maddison and Maximilian Igl and Frank Wood and Yee Whye Teh},
journal= {arXiv preprint arXiv:1802.04537},
year = {2019}
}
Comments
To appear at ICML 2018