Beyond ELBOs: A Large-Scale Evaluation of Variational Methods for Sampling

TL;DR

This paper introduces a comprehensive benchmark for evaluating sampling methods, including Monte Carlo and Variational Inference, across diverse tasks with standardized metrics, addressing previous evaluation inconsistencies.

Contribution

It provides a unified evaluation framework, introduces new metrics for mode collapse, and offers insights into the strengths and weaknesses of current sampling methods.

Findings

Existing methods vary in performance across tasks.

New metrics effectively quantify mode collapse.

Benchmark facilitates fair comparison of sampling techniques.

Abstract

Monte Carlo methods, Variational Inference, and their combinations play a pivotal role in sampling from intractable probability distributions. However, current studies lack a unified evaluation framework, relying on disparate performance measures and limited method comparisons across diverse tasks, complicating the assessment of progress and hindering the decision-making of practitioners. In response to these challenges, our work introduces a benchmark that evaluates sampling methods using a standardized task suite and a broad range of performance criteria. Moreover, we study existing metrics for quantifying mode collapse and introduce novel metrics for this purpose. Our findings provide insights into strengths and weaknesses of existing sampling methods, serving as a valuable reference for future developments. The code is publicly available here.