Accelerating Look-ahead in Bayesian Optimization: Multilevel Monte Carlo is All you Need

Shangda Yang, Vitaly Zankin, Maximilian Balandat, Stefan Scherer, Kevin Carlberg +2 more
2/3/2024
stat.MLcs.LGmath.OC

Official code: Shangda-Yang/MLMCBO (4 stars, MIT, last commit 2026-02-12).

Abstract

We leverage multilevel Monte Carlo (MLMC) to improve the performance of multi-step look-ahead Bayesian optimization (BO) methods that involve nested expectations and maximizations. Often these expectations must be computed by Monte Carlo (MC). The complexity rate of naive MC degrades for nested operations, whereas MLMC is capable of achieving the canonical MC convergence rate for this type of problem, independently of dimension and without any smoothness assumptions. Our theoretical study focuses on the approximation improvements for twoand three-step look-ahead acquisition functions, but, as we discuss, the approach is generalizable in various ways, including beyond the context of BO. Our findings are verified numerically and the benefits of MLMC for BO are illustrated on several benchmark examples. Code is available at https://github.com/Shangda-Yang/MLMCBO .

View on arXivView PDF

Code Implementations(1)

Shangda-Yang/MLMCBOOfficial100%
MIT
40PythonMay 1, 20238 months agoMIT

Similar Papers

EARL-BO: Reinforcement Learning for Multi-Step Lookahead, High-Dimensional Bayesian Optimization

82% match2024

Accelerating Multilevel Markov Chain Monte Carlo Using Machine Learning Models

82% match2024

Improving sample efficiency of high dimensional Bayesian optimization with MCMC

82% match2024

None To Optima in Few Shots: Bayesian Optimization with MDP Priors

81% match2025

Scalable Monte Carlo for Bayesian Learning

81% match1 repo52024

Vanilla Bayesian Optimization Performs Great in High Dimensions

81% match1 repo392026

Cite this paper

@article{yang2024accelerating,
  title  = {Accelerating Look-ahead in Bayesian Optimization: Multilevel Monte Carlo is All you Need},
  author = {Shangda Yang and Vitaly Zankin and Maximilian Balandat and Stefan Scherer and Kevin Carlberg and Neil Walton and Kody J. H. Law},
  year   = {2024},
  eprint = {2402.02111},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2402.02111v2},
  journal = {ICML 2024 2024}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2402.02111.svg)](https://codeofpaper.com/paper/2402.02111)

Discussion