The TAP free energy for high-dimensional linear regression
Probability
2022-03-16 v1 Statistics Theory
Machine Learning
Statistics Theory
Abstract
We derive a variational representation for the log-normalizing constant of the posterior distribution in Bayesian linear regression with a uniform spherical prior and an i.i.d. Gaussian design. We work under the "proportional" asymptotic regime, where the number of observations and the number of features grow at a proportional rate. This rigorously establishes the Thouless-Anderson-Palmer (TAP) approximation arising from spin glass theory, and proves a conjecture of Krzakala et. al. (2014) in the special case of the spherical prior.
Cite
@article{arxiv.2203.07539,
title = {The TAP free energy for high-dimensional linear regression},
author = {Jiaze Qiu and Subhabrata Sen},
journal= {arXiv preprint arXiv:2203.07539},
year = {2022}
}
Comments
36 pages