18
0

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

Abstract

The kk-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 kk-parity problem with stochastic gradient descent (SGD) on two-layer fully-connected neural networks. We demonstrate that SGD can efficiently solve the kk-sparse parity problem on a dd-dimensional hypercube (kO(d)k\le O(\sqrt{d})) with a sample complexity of O~(dk1)\tilde{O}(d^{k-1}) using 2Θ(k)2^{\Theta(k)} neurons, thus matching the established Ω(dk)\Omega(d^{k}) lower bounds of Statistical Query (SQ) models. Our theoretical analysis begins by constructing a good neural network capable of correctly solving the kk-parity problem. We then demonstrate how a trained neural network with SGD can effectively approximate this good network, solving the kk-parity problem with small statistical errors. Our theoretical results and findings are supported by empirical evidence, showcasing the efficiency and efficacy of our approach.

View on arXiv
Comments on this paper