Vanishing success probability for stable algorithms in the asymmetric binary perceptron
Show that for the asymmetric binary perceptron with Gaussian disorder, any algorithm that is ℓ2-stable under a small Gaussian resampling of the disorder (as in Theorem 1.1) has success probability oN(1) for locating an ιN-isolated solution, where "locating" means outputting a vector within ℓ2-distance √(ιN)/3 of some ιN-isolated Boolean solution.
References
Strengthening the algorithmic success probability ruled out by Theorem~\ref{thm:stable-v1} is to us the most natural and interesting open problem. Show that stable algorithms cannot locate an isolated solution (in the sense of Theorem~\ref{thm:stable-v1}) with probability more than $o_N(1)$.
These results suggest that the algorithmic threshold of the ABP is governed by the rare well-connected structures rather than by the typical solutions, and whether it coincides with the disappearance of these structures remains open Question~1.