DeepAI AI Chat
Log In Sign Up

The Overlap Gap Property in Principal Submatrix Recovery

by   David Gamarnik, et al.
University of Waterloo
Harvard University

We study support recovery for a k × k principal submatrix with elevated mean λ/N, hidden in an N× N symmetric mean zero Gaussian matrix. Here λ>0 is a universal constant, and we assume k = N ρ for some constant ρ∈ (0,1). We establish that the MLE recovers a constant proportion of the hidden submatrix if and only if λ≳√(1/ρlog1/ρ). The MLE is computationally intractable in general, and in fact, for ρ>0 sufficiently small, this problem is conjectured to exhibit a statistical-computational gap. To provide rigorous evidence for this, we study the likelihood landscape for this problem, and establish that for some ε>0 and √(1/ρlog1/ρ)≪λ≪1/ρ^1/2 + ε, the problem exhibits a variant of the Overlap-Gap-Property(OGP). As a direct consequence, we establish that a family of local MCMC based algorithms do not achieve optimal recovery. Finally, we establish that for λ > 1/ρ, a simple spectral method recovers a constant proportion of the hidden submatrix.


page 1

page 2

page 3

page 4


Sparse High-Dimensional Linear Regression. Algorithmic Barriers and a Local Search Algorithm

We consider a sparse high dimensional regression model where the goal is...

The Landscape of the Planted Clique Problem: Dense subgraphs and the Overlap Gap Property

In this paper we study the computational-statistical gap of the planted ...

Algorithmic Obstructions in the Random Number Partitioning Problem

We consider the algorithmic problem of finding a near-optimal solution f...

Densest Subgraphs of a Dense Erdös-Rényi Graph. Asymptotics, Landscape and Universality

We consider the problem of estimating the edge density of densest K-node...

Delegated Pandora's box

In delegation problems, a principal does not have the resources necessar...

Group testing and local search: is there a computational-statistical gap?

In this work we study the fundamental limits of approximate recovery in ...

Geometric Barriers for Stable and Online Algorithms for Discrepancy Minimization

For many computational problems involving randomness, intricate geometri...