Saved in:
Bibliographic Details
Main Authors: Blessing, Denis, Jia, Xiaogang, Esslinger, Johannes, Vargas, Francisco, Neumann, Gerhard
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2406.07423
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911913707831296
author Blessing, Denis
Jia, Xiaogang
Esslinger, Johannes
Vargas, Francisco
Neumann, Gerhard
author_facet Blessing, Denis
Jia, Xiaogang
Esslinger, Johannes
Vargas, Francisco
Neumann, Gerhard
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2406_07423
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Beyond ELBOs: A Large-Scale Evaluation of Variational Methods for Sampling
Blessing, Denis
Jia, Xiaogang
Esslinger, Johannes
Vargas, Francisco
Neumann, Gerhard
Machine Learning
Artificial Intelligence
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.
title Beyond ELBOs: A Large-Scale Evaluation of Variational Methods for Sampling
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2406.07423