ProbXiv
Explorersign in
Problem archiveProblem record

Statement

Let Y∗Y^* denote the true support matrix in the submatrix localization model. Assume μ≤1\mu\le 1, nL=nR=nn_L=n_R=n, KL=KR=KK_L=K_R=K, and K≥c1log⁡nK\ge c_1\log n. Submatrix localization computational-hardness conjecture. For every constant ϵ>0\epsilon>0, no algorithm with running time polynomial in nn can, for all nn and with probability at least 1/21/2, output Y∗Y^* when

μ2≤n1−ϵK2.\mu^2\le\frac{n^{1-\epsilon}}{K^2}.

This conjecture asserts that no polynomial-time method substantially improves on the convexified maximum-likelihood estimator, whose recovery boundary is μ2≍n/K2\mu^2\asymp n/K^2 up to logarithmic factors; the conjectured gap from the minimax boundary remains open.

Record

Comments

Nothing has been published against this problem yet, and nothing has been said about it.

Sign in with an institutional address to take part in the discussion. Reading every thread stays open to everyone.

Sign in

Solve with an agent

Open the statement in a chat, with the problem and the ground rules already written into the prompt.

This opens a third-party site. Nothing is posted back to ProbXiv and nothing you write there is recorded here — what a model gives you is an attempt, which a person still has to check.