Quantum speedups for stochastic optimization

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Sidford, Aaron, Zhang, Chenyi
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910540432932864
author Sidford, Aaron
Zhang, Chenyi
author_facet Sidford, Aaron
Zhang, Chenyi
contents We consider the problem of minimizing a continuous function given quantum access to a stochastic gradient oracle. We provide two new methods for the special case of minimizing a Lipschitz convex function. Each method obtains a dimension versus accuracy trade-off which is provably unachievable classically and we prove that one method is asymptotically optimal in low-dimensional settings. Additionally, we provide quantum algorithms for computing a critical point of a smooth non-convex function at rates not known to be achievable classically. To obtain these results we build upon the quantum multivariate mean estimation result of Cornelissen et al. 2022 and provide a general quantum-variance reduction technique of independent interest.
format Preprint
id arxiv_https___arxiv_org_abs_2308_01582
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Quantum speedups for stochastic optimization
Sidford, Aaron
Zhang, Chenyi
Quantum Physics
Data Structures and Algorithms
Optimization and Control
We consider the problem of minimizing a continuous function given quantum access to a stochastic gradient oracle. We provide two new methods for the special case of minimizing a Lipschitz convex function. Each method obtains a dimension versus accuracy trade-off which is provably unachievable classically and we prove that one method is asymptotically optimal in low-dimensional settings. Additionally, we provide quantum algorithms for computing a critical point of a smooth non-convex function at rates not known to be achievable classically. To obtain these results we build upon the quantum multivariate mean estimation result of Cornelissen et al. 2022 and provide a general quantum-variance reduction technique of independent interest.
title Quantum speedups for stochastic optimization
topic Quantum Physics
Data Structures and Algorithms
Optimization and Control
url https://arxiv.org/abs/2308.01582