Enregistré dans:
Détails bibliographiques
Auteurs principaux: Yi, Zeji, Wei, Yunyue, Cheng, Chu Xin, He, Kaibo, Sui, Yanan
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2401.02650
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866913186671755264
author Yi, Zeji
Wei, Yunyue
Cheng, Chu Xin
He, Kaibo
Sui, Yanan
author_facet Yi, Zeji
Wei, Yunyue
Cheng, Chu Xin
He, Kaibo
Sui, Yanan
contents Sequential optimization methods are often confronted with the curse of dimensionality in high-dimensional spaces. Current approaches under the Gaussian process framework are still burdened by the computational complexity of tracking Gaussian process posteriors and need to partition the optimization problem into small regions to ensure exploration or assume an underlying low-dimensional structure. With the idea of transiting the candidate points towards more promising positions, we propose a new method based on Markov Chain Monte Carlo to efficiently sample from an approximated posterior. We provide theoretical guarantees of its convergence in the Gaussian process Thompson sampling setting. We also show experimentally that both the Metropolis-Hastings and the Langevin Dynamics version of our algorithm outperform state-of-the-art methods in high-dimensional sequential optimization and reinforcement learning benchmarks.
format Preprint
id arxiv_https___arxiv_org_abs_2401_02650
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Improving sample efficiency of high dimensional Bayesian optimization with MCMC
Yi, Zeji
Wei, Yunyue
Cheng, Chu Xin
He, Kaibo
Sui, Yanan
Machine Learning
Sequential optimization methods are often confronted with the curse of dimensionality in high-dimensional spaces. Current approaches under the Gaussian process framework are still burdened by the computational complexity of tracking Gaussian process posteriors and need to partition the optimization problem into small regions to ensure exploration or assume an underlying low-dimensional structure. With the idea of transiting the candidate points towards more promising positions, we propose a new method based on Markov Chain Monte Carlo to efficiently sample from an approximated posterior. We provide theoretical guarantees of its convergence in the Gaussian process Thompson sampling setting. We also show experimentally that both the Metropolis-Hastings and the Langevin Dynamics version of our algorithm outperform state-of-the-art methods in high-dimensional sequential optimization and reinforcement learning benchmarks.
title Improving sample efficiency of high dimensional Bayesian optimization with MCMC
topic Machine Learning
url https://arxiv.org/abs/2401.02650