Saved in:
Bibliographic Details
Main Authors: Li, Diantong, Cho, Kyunghyun, Liu, Chong
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.01006
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911246715977728
author Li, Diantong
Cho, Kyunghyun
Liu, Chong
author_facet Li, Diantong
Cho, Kyunghyun
Liu, Chong
contents Bayesian Optimization (BO) is an efficient tool for optimizing black-box functions, but its theoretical guarantees typically hold in the asymptotic regime. In many critical real-world applications such as drug discovery or materials design, where each evaluation can be very costly and time-consuming, BO becomes impractical for many evaluations. In this paper, we introduce the Procedure-inFormed BO (ProfBO) algorithm, which solves black-box optimization with remarkably few function evaluations. At the heart of our algorithmic design are Markov Decision Process (MDP) priors that model optimization trajectories from related source tasks, thereby capturing procedural knowledge on efficient optimization. We embed these MDP priors into a prior-fitted neural network and employ model-agnostic meta-learning for fast adaptation to new target tasks. Experiments on real-world Covid and Cancer benchmarks and hyperparameter tuning tasks demonstrate that ProfBO consistently outperforms state-of-the-art methods by achieving high-quality solutions with significantly fewer evaluations, making it ready for practical deployment.
format Preprint
id arxiv_https___arxiv_org_abs_2511_01006
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle None To Optima in Few Shots: Bayesian Optimization with MDP Priors
Li, Diantong
Cho, Kyunghyun
Liu, Chong
Machine Learning
Bayesian Optimization (BO) is an efficient tool for optimizing black-box functions, but its theoretical guarantees typically hold in the asymptotic regime. In many critical real-world applications such as drug discovery or materials design, where each evaluation can be very costly and time-consuming, BO becomes impractical for many evaluations. In this paper, we introduce the Procedure-inFormed BO (ProfBO) algorithm, which solves black-box optimization with remarkably few function evaluations. At the heart of our algorithmic design are Markov Decision Process (MDP) priors that model optimization trajectories from related source tasks, thereby capturing procedural knowledge on efficient optimization. We embed these MDP priors into a prior-fitted neural network and employ model-agnostic meta-learning for fast adaptation to new target tasks. Experiments on real-world Covid and Cancer benchmarks and hyperparameter tuning tasks demonstrate that ProfBO consistently outperforms state-of-the-art methods by achieving high-quality solutions with significantly fewer evaluations, making it ready for practical deployment.
title None To Optima in Few Shots: Bayesian Optimization with MDP Priors
topic Machine Learning
url https://arxiv.org/abs/2511.01006