Computational Hardness of Certifying Bounds on Constrained PCA Problems

02/19/2019
by   Afonso S. Bandeira, et al.
0

Given a random n × n symmetric matrix W drawn from the Gaussian orthogonal ensemble (GOE), we consider the problem of certifying an upper bound on the maximum value of the quadratic form x^ W x over all vectors x in a constraint set S⊂R^n. For a certain class of normalized constraint sets S, we give strong evidence that there is no polynomial-time algorithm certifying a better upper bound than the largest eigenvalue of W. A notable special case included in our results is the hypercube S = {± 1 / √(n)}^n, which corresponds to the problem of certifying bounds on the Hamiltonian of the Sherrington-Kirkpatrick spin glass model from statistical physics. Our proof proceeds in two steps. First, we give a reduction from the detection problem in the negatively-spiked Wishart model to the above certification problem. We then give evidence that this Wishart detection problem is computationally hard below the classical spectral threshold, using a method of Hopkins and Steurer based on approximating the likelihood ratio with a low-degree polynomial. Our proof can be seen as constructing a distribution over symmetric matrices that appears computationally indistinguishable from the GOE, yet is supported on matrices whose maximum quadratic form over x ∈S is much larger than that of a GOE matrix.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/27/2020

Spectral Planting and the Hardness of Refuting Cuts, Colorability, and Communities in Random Graphs

We study the problem of efficiently refuting the k-colorability of a gra...
research
12/04/2022

Notes on the complexity of coverings for Kronecker powers of symmetric matrices

In the present note, we study a new method of constructing efficient cov...
research
08/16/2023

Expected Euler characteristic method for the largest eigenvalue: (Skew-)orthogonal polynomial approach

The expected Euler characteristic (EEC) method is an integral-geometric ...
research
09/27/2019

Edge Expansion and Spectral Gap of Nonnegative Matrices

The classic graphical Cheeger inequalities state that if M is an n× n sy...
research
11/07/2019

Linear Constrained Rayleigh Quotient Optimization: Theory and Algorithms

We consider the following constrained Rayleigh quotient optimization pro...
research
05/31/2021

Optimal Spectral Recovery of a Planted Vector in a Subspace

Recovering a planted vector v in an n-dimensional random subspace of ℝ^N...
research
09/29/2022

The behaviour of the Gauss-Radau upper bound of the error norm in CG

Consider the problem of solving systems of linear algebraic equations Ax...

Please sign up or login with your details

Forgot password? Click here to reset