Quantum Algorithms for Non-smooth Non-convex Optimization

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Liu, Chengchang, Guan, Chaowen, He, Jianhao, Lui, John C. S.
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909357809074176
author Liu, Chengchang
Guan, Chaowen
He, Jianhao
Lui, John C. S.
author_facet Liu, Chengchang
Guan, Chaowen
He, Jianhao
Lui, John C. S.
contents This paper considers the problem for finding the $(δ,ε)$-Goldstein stationary point of Lipschitz continuous objective, which is a rich function class to cover a great number of important applications. We construct a zeroth-order quantum estimator for the gradient of the smoothed surrogate. Based on such estimator, we propose a novel quantum algorithm that achieves a query complexity of $\tilde{\mathcal{O}}(d^{3/2}δ^{-1}ε^{-3})$ on the stochastic function value oracle, where $d$ is the dimension of the problem. We also enhance the query complexity to $\tilde{\mathcal{O}}(d^{3/2}δ^{-1}ε^{-7/3})$ by introducing a variance reduction variant. Our findings demonstrate the clear advantages of utilizing quantum techniques for non-convex non-smooth optimization, as they outperform the optimal classical methods on the dependency of $ε$ by a factor of $ε^{-2/3}$.
format Preprint
id arxiv_https___arxiv_org_abs_2410_16189
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Quantum Algorithms for Non-smooth Non-convex Optimization
Liu, Chengchang
Guan, Chaowen
He, Jianhao
Lui, John C. S.
Quantum Physics
Optimization and Control
This paper considers the problem for finding the $(δ,ε)$-Goldstein stationary point of Lipschitz continuous objective, which is a rich function class to cover a great number of important applications. We construct a zeroth-order quantum estimator for the gradient of the smoothed surrogate. Based on such estimator, we propose a novel quantum algorithm that achieves a query complexity of $\tilde{\mathcal{O}}(d^{3/2}δ^{-1}ε^{-3})$ on the stochastic function value oracle, where $d$ is the dimension of the problem. We also enhance the query complexity to $\tilde{\mathcal{O}}(d^{3/2}δ^{-1}ε^{-7/3})$ by introducing a variance reduction variant. Our findings demonstrate the clear advantages of utilizing quantum techniques for non-convex non-smooth optimization, as they outperform the optimal classical methods on the dependency of $ε$ by a factor of $ε^{-2/3}$.
title Quantum Algorithms for Non-smooth Non-convex Optimization
topic Quantum Physics
Optimization and Control
url https://arxiv.org/abs/2410.16189