Quantum Speedups for Markov Chain Monte Carlo Methods with Application to Optimization

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Ozgul, Guneykan, Li, Xiantao, Mahdavi, Mehrdad, Wang, Chunhao
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910903679582208
author Ozgul, Guneykan
Li, Xiantao
Mahdavi, Mehrdad
Wang, Chunhao
author_facet Ozgul, Guneykan
Li, Xiantao
Mahdavi, Mehrdad
Wang, Chunhao
contents We propose quantum algorithms that provide provable speedups for Markov Chain Monte Carlo (MCMC) methods commonly used for sampling from probability distributions of the form $π\propto e^{-f}$, where $f$ is a potential function. Our first approach considers Gibbs sampling for finite-sum potentials in the stochastic setting, employing an oracle that provides gradients of individual functions. In the second setting, we consider access only to a stochastic evaluation oracle, allowing simultaneous queries at two points of the potential function under the same stochastic parameter. By introducing novel techniques for stochastic gradient estimation, our algorithms improve the gradient and evaluation complexities of classical samplers, such as Hamiltonian Monte Carlo (HMC) and Langevin Monte Carlo (LMC) in terms of dimension, precision, and other problem-dependent parameters. Furthermore, we achieve quantum speedups in optimization, particularly for minimizing non-smooth and approximately convex functions that commonly appear in empirical risk minimization problems.
format Preprint
id arxiv_https___arxiv_org_abs_2504_03626
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Quantum Speedups for Markov Chain Monte Carlo Methods with Application to Optimization
Ozgul, Guneykan
Li, Xiantao
Mahdavi, Mehrdad
Wang, Chunhao
Quantum Physics
Machine Learning
Optimization and Control
We propose quantum algorithms that provide provable speedups for Markov Chain Monte Carlo (MCMC) methods commonly used for sampling from probability distributions of the form $π\propto e^{-f}$, where $f$ is a potential function. Our first approach considers Gibbs sampling for finite-sum potentials in the stochastic setting, employing an oracle that provides gradients of individual functions. In the second setting, we consider access only to a stochastic evaluation oracle, allowing simultaneous queries at two points of the potential function under the same stochastic parameter. By introducing novel techniques for stochastic gradient estimation, our algorithms improve the gradient and evaluation complexities of classical samplers, such as Hamiltonian Monte Carlo (HMC) and Langevin Monte Carlo (LMC) in terms of dimension, precision, and other problem-dependent parameters. Furthermore, we achieve quantum speedups in optimization, particularly for minimizing non-smooth and approximately convex functions that commonly appear in empirical risk minimization problems.
title Quantum Speedups for Markov Chain Monte Carlo Methods with Application to Optimization
topic Quantum Physics
Machine Learning
Optimization and Control
url https://arxiv.org/abs/2504.03626