37
2

Quantum Algorithms and Lower Bounds for Finite-Sum Optimization

Abstract

Finite-sum optimization has wide applications in machine learning, covering important problems such as support vector machines, regression, etc. In this paper, we initiate the study of solving finite-sum optimization problems by quantum computing. Specifically, let f1,,fn ⁣:RdRf_1,\ldots,f_n\colon\mathbb{R}^d\to\mathbb{R} be \ell-smooth convex functions and ψ ⁣:RdR\psi\colon\mathbb{R}^d\to\mathbb{R} be a μ\mu-strongly convex proximal function. The goal is to find an ϵ\epsilon-optimal point for F(x)=1ni=1nfi(x)+ψ(x)F(\mathbf{x})=\frac{1}{n}\sum_{i=1}^n f_i(\mathbf{x})+\psi(\mathbf{x}). We give a quantum algorithm with complexity O~(n+d+/μ(n1/3d1/3+n2/3d5/6))\tilde{O}\big(n+\sqrt{d}+\sqrt{\ell/\mu}\big(n^{1/3}d^{1/3}+n^{-2/3}d^{5/6}\big)\big), improving the classical tight bound Θ~(n+n/μ)\tilde{\Theta}\big(n+\sqrt{n\ell/\mu}\big). We also prove a quantum lower bound Ω~(n+n3/4(/μ)1/4)\tilde{\Omega}(n+n^{3/4}(\ell/\mu)^{1/4}) when dd is large enough. Both our quantum upper and lower bounds can extend to the cases where ψ\psi is not necessarily strongly convex, or each fif_i is Lipschitz but not necessarily smooth. In addition, when FF is nonconvex, our quantum algorithm can find an ϵ\epsilon-critial point using O~(n+(d1/3n1/3+d)/ϵ2)\tilde{O}(n+\ell(d^{1/3}n^{1/3}+\sqrt{d})/\epsilon^2) queries.

View on arXiv
Comments on this paper