Revisiting Unbiased Implicit Variational Inference

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Pielok, Tobias, Bischl, Bernd, Rügamer, David
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918045468852224
author Pielok, Tobias
Bischl, Bernd
Rügamer, David
author_facet Pielok, Tobias
Bischl, Bernd
Rügamer, David
contents Recent years have witnessed growing interest in semi-implicit variational inference (SIVI) methods due to their ability to rapidly generate samples from complex distributions. However, since the likelihood of these samples is non-trivial to estimate in high dimensions, current research focuses on finding effective SIVI training routines. Although unbiased implicit variational inference (UIVI) has largely been dismissed as imprecise and computationally prohibitive because of its inner MCMC loop, we revisit this method and show that UIVI's MCMC loop can be effectively replaced via importance sampling and the optimal proposal distribution can be learned stably by minimizing an expected forward Kullback-Leibler divergence without bias. Our refined approach demonstrates superior performance or parity with state-of-the-art methods on established SIVI benchmarks.
format Preprint
id arxiv_https___arxiv_org_abs_2506_03839
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Revisiting Unbiased Implicit Variational Inference
Pielok, Tobias
Bischl, Bernd
Rügamer, David
Machine Learning
62F15, 68T07
I.2.6; G.3
Recent years have witnessed growing interest in semi-implicit variational inference (SIVI) methods due to their ability to rapidly generate samples from complex distributions. However, since the likelihood of these samples is non-trivial to estimate in high dimensions, current research focuses on finding effective SIVI training routines. Although unbiased implicit variational inference (UIVI) has largely been dismissed as imprecise and computationally prohibitive because of its inner MCMC loop, we revisit this method and show that UIVI's MCMC loop can be effectively replaced via importance sampling and the optimal proposal distribution can be learned stably by minimizing an expected forward Kullback-Leibler divergence without bias. Our refined approach demonstrates superior performance or parity with state-of-the-art methods on established SIVI benchmarks.
title Revisiting Unbiased Implicit Variational Inference
topic Machine Learning
62F15, 68T07
I.2.6; G.3
url https://arxiv.org/abs/2506.03839