Discrepancy Algorithms for the Binary Perceptron

The binary perceptron problem asks us to find a sign vector in the intersection of independently chosen random halfspaces with intercept $-\kappa$. We analyze the performance of the canonical discrepancy minimization algorithms of Lovett-Meka and Rothvoss/Eldan-Singh for the asymmetric binary perceptron problem. We obtain new algorithmic results in the $\kappa =0$ case and in the large-$\mathrm{\mid }\kappa \mathrm{\mid }$ case. In the $\kappa \to -\mathrm{\infty }$ case, we additionally characterize the storage capacity and complement our algorithmic results with an almost-matching overlap-gap lower bound.