Constrained Low-rank Matrix Estimation: Phase Transitions, Approximate Message Passing and Applications

TL;DR

This paper develops a unified framework for constrained low-rank matrix estimation, connecting statistical physics models with practical algorithms like Low-RAMP, and analyzes phase transitions affecting inference performance.

Contribution

It introduces a general approach to study constrained low-rank matrix estimation, deriving the Low-RAMP algorithm and analyzing phase transitions in inference.

Findings

Derivation of the Low-RAMP algorithm for various models

Analysis of phase diagrams and phase transitions in inference

Unification of statistical physics models with matrix estimation techniques

Abstract

This article is an extended version of previous work of the authors [40, 41] on low-rank matrix estimation in the presence of constraints on the factors into which the matrix is factorized. Low-rank matrix factorization is one of the basic methods used in data analysis for unsupervised learning of relevant features and other types of dimensionality reduction. We present a framework to study the constrained low-rank matrix estimation for a general prior on the factors, and a general output channel through which the matrix is observed. We draw a paralel with the study of vector-spin glass models - presenting a unifying way to study a number of problems considered previously in separate statistical physics works. We present a number of applications for the problem in data analysis. We derive in detail a general form of the low-rank approximate message passing (Low- RAMP) algorithm, that is known in statistical physics as the TAP equations. We thus unify the derivation of the TAP equations for models as different as the Sherrington-Kirkpatrick model, the restricted Boltzmann machine, the Hopfield model or vector (xy, Heisenberg and other) spin glasses. The state evolution of the Low-RAMP algorithm is also derived, and is equivalent to the replica symmetric solution for the large class of vector-spin glass models. In the section devoted to result we study in detail phase diagrams and phase transitions for the Bayes-optimal inference in low-rank matrix estimation. We present a typology of phase transitions and their relation to performance of algorithms such as the Low-RAMP or commonly used spectral methods.