Relay Variational Inference: A Method for Accelerated Encoderless VI

TL;DR

Relay VI (RVI) is a novel framework that significantly accelerates convergence and enhances performance in encoderless variational inference, especially useful for handling missing data and complex models.

Contribution

Introduces Relay VI (RVI), a new method that improves convergence speed and performance of encoderless variational inference models.

Findings

RVI outperforms existing encoderless VI methods in convergence speed.

RVI achieves better loss and representation quality.

RVI effectively handles missing data imputation.

Abstract

Variational Inference (VI) offers a method for approximating intractable likelihoods. In neural VI, inference of approximate posteriors is commonly done using an encoder. Alternatively, encoderless VI offers a framework for learning generative models from data without encountering suboptimalities caused by amortization via an encoder (e.g. in presence of missing or uncertain data). However, in absence of an encoder, such methods often suffer in convergence due to the slow nature of gradient steps required to learn the approximate posterior parameters. In this paper, we introduce Relay VI (RVI), a framework that dramatically improves both the convergence and performance of encoderless VI. In our experiments over multiple datasets, we study the effectiveness of RVI in terms of convergence speed, loss, representation power and missing data imputation. We find RVI to be a unique tool, often superior in both performance and convergence speed to previously proposed encoderless as well as amortized VI models (e.g. VAE).