Rank-one matrix estimation: analytic time evolution of gradient descent dynamics

05/25/2021
by   Antoine Bodin, et al.
0

We consider a rank-one symmetric matrix corrupted by additive noise. The rank-one matrix is formed by an n-component unknown vector on the sphere of radius √(n), and we consider the problem of estimating this vector from the corrupted matrix in the high dimensional limit of n large, by gradient descent for a quadratic cost function on the sphere. Explicit formulas for the whole time evolution of the overlap between the estimator and unknown vector, as well as the cost, are rigorously derived. In the long time limit we recover the well known spectral phase transition, as a function of the signal-to-noise ratio. The explicit formulas also allow to point out interesting transient features of the time evolution. Our analysis technique is based on recent progress in random matrix theory and uses local versions of the semi-circle law.

READ FULL TEXT
research
11/12/2019

0-1 phase transitions in sparse spiked matrix estimation

We consider statistical models of estimation of a rank-one matrix (the s...
research
01/02/2010

Regularization for Matrix Completion

We consider the problem of reconstructing a low rank matrix from noisy o...
research
02/07/2023

Mismatched estimation of non-symmetric rank-one matrices corrupted by structured noise

We study the performance of a Bayesian statistician who estimates a rank...
research
11/15/2017

The landscape of the spiked tensor model

We consider the problem of estimating a large rank-one tensor u^⊗ k∈( R...
research
04/09/2022

High-dimensional Asymptotics of Langevin Dynamics in Spiked Matrix Models

We study Langevin dynamics for recovering the planted signal in the spik...
research
11/01/2022

Fundamental Limits of Low-Rank Matrix Estimation with Diverging Aspect Ratios

We consider the problem of estimating the factors of a low-rank n × d ma...
research
06/07/2023

Bayesian Extensive-Rank Matrix Factorization with Rotational Invariant Priors

We consider a statistical model for matrix factorization in a regime whe...

Please sign up or login with your details

Forgot password? Click here to reset