Approximate Stein Classes for Truncated Density Estimation

Daniel J Williams, Song Liu

Research output: Chapter in Book/Report/Conference proceedingConference Contribution (Conference Proceeding)

Abstract

Estimating truncated density models is difficult, as these models have intractable normalising constants and hard to satisfy boundary conditions. Score matching can be adapted to solve the truncated density estimation problem, but requires a continuous weighting function which takes zero at the boundary and is positive elsewhere. Evaluation of such a weighting function (and its gradient) often requires a closed-form expression of the truncation boundary and finding a solution to a complicated optimisation problem. In this paper, we propose approximate Stein classes, which in turn leads to a relaxed Stein identity for truncated density estimation. We develop a novel discrepancy measure, truncated kernelised Stein discrepancy (TKSD), which does not require fixing a weighting function in advance, and can be evaluated using only samples on the boundary. We estimate a truncated density model by minimising the Lagrangian dual of TKSD. Finally, experiments show the accuracy of our method to be an improvement over previous works even without the explicit functional form of the boundary.
Original languageEnglish
Title of host publicationInternational Conference on Machine Learning (ICML 2023)
EditorsAndreas Krause, Emma Brunskill, Kyunghyun Cho, Barbara Engelhardt, Sivan Sabato, Jonathan Scarlett
PublisherProceedings of Machine Learning Research
Pages37066-37090
Number of pages25
ISBN (Electronic)9781713889182
Publication statusPublished - 1 Feb 2024
EventInternational Conference on Machine Learning - Hawaii, Honolulu, United States
Duration: 23 Jul 202329 Jul 2023
Conference number: 2023

Publication series

NameProceedings of Machine Learning Research
PublisherProceedings of Machine Learning Research
Volume202
ISSN (Electronic)2640-3498

Conference

ConferenceInternational Conference on Machine Learning
Abbreviated titleICML
Country/TerritoryUnited States
CityHonolulu
Period23/07/2329/07/23

Fingerprint

Dive into the research topics of 'Approximate Stein Classes for Truncated Density Estimation'. Together they form a unique fingerprint.

Cite this