0-1 phase transitions in sparse spiked matrix estimation

11/12/2019
by   Jean Barbier, et al.
0

We consider statistical models of estimation of a rank-one matrix (the spike) corrupted by an additive gaussian noise matrix in the sparse limit. In this limit the underlying hidden vector (that constructs the rank-one matrix) has a number of non-zero components that scales sub-linearly with the total dimension of the vector, and the signal strength tends to infinity at an appropriate speed. We prove explicit low-dimensional variational formulas for the asymptotic mutual information between the spike and the observed noisy matrix in suitable sparse limits. For Bernoulli and Bernoulli-Rademacher distributed vectors, and when the sparsity and signal strength satisfy an appropriate scaling relation, these formulas imply sharp 0-1 phase transitions for the asymptotic minimum mean-square-error. A similar phase transition was analyzed recently in the context of sparse high-dimensional linear regression (compressive sensing).

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

06/14/2020

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

We determine statistical and computational limits for estimation of a ra...
05/25/2021

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

We consider a rank-one symmetric matrix corrupted by additive noise. The...
06/26/2020

Tensor estimation with structured priors

We consider rank-one symmetric tensor estimation when the tensor is corr...
01/27/2021

The fundamental limits of sparse linear regression with sublinear sparsity

We establish exact asymptotic expressions for the normalized mutual info...
06/19/2020

Information theoretic limits of learning a sparse rule

We consider generalized linear models in regimes where the number of non...
04/15/2020

High-dimensional rank-one nonsymmetric matrix decomposition: the spherical case

We consider the problem of estimating a rank-one nonsymmetric matrix und...
01/19/2019

The adaptive interpolation method for proving replica formulas. Applications to the Curie-Weiss and Wigner spike models

In this contribution we give a pedagogic introduction to the newly intro...
This week in AI

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