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

by   Antoine Bodin, et al.

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.



There are no comments yet.


page 5


0-1 phase transitions in sparse spiked matrix estimation

We consider statistical models of estimation of a rank-one matrix (the s...

Regularization for Matrix Completion

We consider the problem of reconstructing a low rank matrix from noisy o...

All-or-nothing statistical and computational phase transitions in sparse spiked matrix estimation

We determine statistical and computational limits for estimation of a ra...

The landscape of the spiked tensor model

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

High-dimensional Asymptotics of Langevin Dynamics in Spiked Matrix Models

We study Langevin dynamics for recovering the planted signal in the spik...

Two equalities expressing the determinant of a matrix in terms of expectations over matrix-vector products

We introduce two equations expressing the inverse determinant of a full ...

Rank-one matrix estimation with groupwise heteroskedasticity

We study the problem of estimating a rank-one matrix from Gaussian obser...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.