DeepAI AI Chat
Log In Sign Up

The Overlap Gap Property in Principal Submatrix Recovery

08/26/2019
by   David Gamarnik, et al.
University of Waterloo
MIT
Harvard University
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

11/14/2017

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

We consider a sparse high dimensional regression model where the goal is...
04/15/2019

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 ...
03/02/2021

Algorithmic Obstructions in the Random Number Partitioning Problem

We consider the algorithmic problem of finding a near-optimal solution f...
12/07/2022

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...
02/21/2022

Delegated Pandora's box

In delegation problems, a principal does not have the resources necessar...
11/10/2020

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

In this work we study the fundamental limits of approximate recovery in ...
02/13/2023

Geometric Barriers for Stable and Online Algorithms for Discrepancy Minimization

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