Computational hardness of submatrix localization below the convexified MLE threshold
Statement
Let denote the true support matrix in the submatrix localization model. Assume , , , and . Submatrix localization computational-hardness conjecture. For every constant , no algorithm with running time polynomial in can, for all and with probability at least , output when
This conjecture asserts that no polynomial-time method substantially improves on the convexified maximum-likelihood estimator, whose recovery boundary is 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 inSolve with an agent
Open the statement in a chat, with the problem and the ground rules already written into the prompt.