Indirect Query Bayesian Optimization with Integrated Feedback

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Zhang, Mengyan, Bouabid, Shahine, Ong, Cheng Soon, Flaxman, Seth, Sejdinovic, Dino
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915444574650368
author Zhang, Mengyan
Bouabid, Shahine
Ong, Cheng Soon
Flaxman, Seth
Sejdinovic, Dino
author_facet Zhang, Mengyan
Bouabid, Shahine
Ong, Cheng Soon
Flaxman, Seth
Sejdinovic, Dino
contents We develop the framework of Indirect Query Bayesian Optimization (IQBO), a new class of Bayesian optimization problems where the integrated feedback is given via a conditional expectation of the unknown function $f$ to be optimized. The underlying conditional distribution can be unknown and learned from data. The goal is to find the global optimum of $f$ by adaptively querying and observing in the space transformed by the conditional distribution. This is motivated by real-world applications where one cannot access direct feedback due to privacy, hardware or computational constraints. We propose the Conditional Max-Value Entropy Search (CMES) acquisition function to address this novel setting, and propose a hierarchical search algorithm with multi-resolution feedback to improve computational efficiency. We show regret bounds for our proposed methods and demonstrate the effectiveness of our approaches on simulated optimization tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2412_13559
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Indirect Query Bayesian Optimization with Integrated Feedback
Zhang, Mengyan
Bouabid, Shahine
Ong, Cheng Soon
Flaxman, Seth
Sejdinovic, Dino
Machine Learning
We develop the framework of Indirect Query Bayesian Optimization (IQBO), a new class of Bayesian optimization problems where the integrated feedback is given via a conditional expectation of the unknown function $f$ to be optimized. The underlying conditional distribution can be unknown and learned from data. The goal is to find the global optimum of $f$ by adaptively querying and observing in the space transformed by the conditional distribution. This is motivated by real-world applications where one cannot access direct feedback due to privacy, hardware or computational constraints. We propose the Conditional Max-Value Entropy Search (CMES) acquisition function to address this novel setting, and propose a hierarchical search algorithm with multi-resolution feedback to improve computational efficiency. We show regret bounds for our proposed methods and demonstrate the effectiveness of our approaches on simulated optimization tasks.
title Indirect Query Bayesian Optimization with Integrated Feedback
topic Machine Learning
url https://arxiv.org/abs/2412.13559