Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Yu, Zhiyuan, Liu, Jingbo
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2506.20768
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914415354314752
author Yu, Zhiyuan
Liu, Jingbo
author_facet Yu, Zhiyuan
Liu, Jingbo
contents Approximate inference is central to Bayesian learning, with variational inference (VI) providing a scalable framework for posterior approximation. While mean-field VI often fails in high dimensions, the more refined Bethe approximation, equivalent to the Thouless-Anderson-Palmer (TAP) free energy in statistical physics, has long been conjectured to capture Bayes-optimal behavior. We prove that the TAP formula holds for Bayesian linear regression with a uniform spherical prior at all noise levels ($Δ>0$), extending the result of Qiu and Sen (2023) in the high-noise regime. Our argument constructs a ridge regression functional that dominates the TAP free energy, yielding the first rigorous analysis of the global optimizer of the non-concave TAP functional for a planted inference model at an arbitrary noise level. This verifies that TAP, rather than mean-field, is the correct variational description in this setting.
format Preprint
id arxiv_https___arxiv_org_abs_2506_20768
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Proof of The TAP Free Energy for High-Dimensional Linear Regression with Spherical Priors at All Temperatures
Yu, Zhiyuan
Liu, Jingbo
Statistics Theory
Approximate inference is central to Bayesian learning, with variational inference (VI) providing a scalable framework for posterior approximation. While mean-field VI often fails in high dimensions, the more refined Bethe approximation, equivalent to the Thouless-Anderson-Palmer (TAP) free energy in statistical physics, has long been conjectured to capture Bayes-optimal behavior. We prove that the TAP formula holds for Bayesian linear regression with a uniform spherical prior at all noise levels ($Δ>0$), extending the result of Qiu and Sen (2023) in the high-noise regime. Our argument constructs a ridge regression functional that dominates the TAP free energy, yielding the first rigorous analysis of the global optimizer of the non-concave TAP functional for a planted inference model at an arbitrary noise level. This verifies that TAP, rather than mean-field, is the correct variational description in this setting.
title Proof of The TAP Free Energy for High-Dimensional Linear Regression with Spherical Priors at All Temperatures
topic Statistics Theory
url https://arxiv.org/abs/2506.20768