Matching the Statistical Query Lower Bound for k-sparse Parity Problems with Stochastic Gradient Descent

arXiv:2404.12376v1 Announce Type: new
Abstract: The $k$-parity problem is a classical problem in computational complexity and algorithmic theory, serving as a key benchmark for understanding computational classes. In this paper, we solve the $k$-parity problem with stochastic gradient descent (SGD) on two-layer fully-connected neural networks. We demonstrate that SGD can efficiently solve the $k$-sparse parity problem on a $d$-dimensional hypercube ($k\le O(\sqrt{d})$) with a sample complexity of $\tilde{O}(d^{k-1})$ using $2^{\Theta(k)}$ neurons, thus matching the established $\Omega(d^{k})$ lower bounds of Statistical …

abstract arxiv benchmark complexity computational cs.lg gradient key layer math.oc networks neural networks paper query solve statistical stat.ml stochastic theory type understanding