Sum-of-Squares Lower Bounds for Sherrington-Kirkpatrick via Planted Affine Planes

by   Mrinalkanti Ghosh, et al.

The Sum-of-Squares (SoS) hierarchy is a semi-definite programming meta-algorithm that captures state-of-the-art polynomial time guarantees for many optimization problems such as Max-k-CSPs and Tensor PCA. On the flip side, a SoS lower bound provides evidence of hardness, which is particularly relevant to average-case problems for which NP-hardness may not be available. In this paper, we consider the following average case problem, which we call the Planted Affine Planes (PAP) problem: Given m random vectors d_1,…,d_m in ℝ^n, can we prove that there is no vector v ∈ℝ^n such that for all u ∈ [m], ⟨ v, d_u⟩^2 = 1? In other words, can we prove that m random vectors are not all contained in two parallel hyperplanes at equal distance from the origin? We prove that for m ≤ n^3/2-ϵ, with high probability, degree-n^Ω(ϵ) SoS fails to refute the existence of such a vector v. When the vectors d_1,…,d_m are chosen from the multivariate normal distribution, the PAP problem is equivalent to the problem of proving that a random n-dimensional subspace of ℝ^m does not contain a boolean vector. As shown by Mohanty–Raghavendra–Xu [STOC 2020], a lower bound for this problem implies a lower bound for the problem of certifying energy upper bounds on the Sherrington-Kirkpatrick Hamiltonian, and so our lower bound implies a degree-n^Ω(ϵ) SoS lower bound for the certification version of the Sherrington-Kirkpatrick problem.



There are no comments yet.


page 1

page 2

page 3

page 4


Sum of squares lower bounds from symmetry and a good story

In this paper, we develop machinery for proving sum of squares lower bou...

A Tight Degree 4 Sum-of-Squares Lower Bound for the Sherrington-Kirkpatrick Hamiltonian

We show that, if W∈R^N × N_sym is drawn from the gaussian orthogonal ens...

A Note on Property Testing Sum of Squares and Multivariate Polynomial Interpolation

In this paper, we investigate property testing whether or not a degree d...

Improved Sum-of-Squares Lower Bounds for Hidden Clique and Hidden Submatrix Problems

Given a large data matrix A∈R^n× n, we consider the problem of determini...

Algorithmic Thresholds for Refuting Random Polynomial Systems

Consider a system of m polynomial equations {p_i(x) = b_i}_i ≤ m of degr...

On the AC^0[⊕] complexity of Andreev's Problem

Andreev's Problem states the following: Given an integer d and a subset ...

New Dependencies of Hierarchies in Polynomial Optimization

We compare four key hierarchies for solving Constrained Polynomial Optim...
This week in AI

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