Joint Composite Latent Space Bayesian Optimization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Maus, Natalie, Lin, Zhiyuan Jerry, Balandat, Maximilian, Bakshy, Eytan
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910520771084288
author Maus, Natalie
Lin, Zhiyuan Jerry
Balandat, Maximilian
Bakshy, Eytan
author_facet Maus, Natalie
Lin, Zhiyuan Jerry
Balandat, Maximilian
Bakshy, Eytan
contents Bayesian Optimization (BO) is a technique for sample-efficient black-box optimization that employs probabilistic models to identify promising input locations for evaluation. When dealing with composite-structured functions, such as f=g o h, evaluating a specific location x yields observations of both the final outcome f(x) = g(h(x)) as well as the intermediate output(s) h(x). Previous research has shown that integrating information from these intermediate outputs can enhance BO performance substantially. However, existing methods struggle if the outputs h(x) are high-dimensional. Many relevant problems fall into this setting, including in the context of generative AI, molecular design, or robotics. To effectively tackle these challenges, we introduce Joint Composite Latent Space Bayesian Optimization (JoCo), a novel framework that jointly trains neural network encoders and probabilistic models to adaptively compress high-dimensional input and output spaces into manageable latent representations. This enables viable BO on these compressed representations, allowing JoCo to outperform other state-of-the-art methods in high-dimensional BO on a wide variety of simulated and real-world problems.
format Preprint
id arxiv_https___arxiv_org_abs_2311_02213
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Joint Composite Latent Space Bayesian Optimization
Maus, Natalie
Lin, Zhiyuan Jerry
Balandat, Maximilian
Bakshy, Eytan
Machine Learning
Bayesian Optimization (BO) is a technique for sample-efficient black-box optimization that employs probabilistic models to identify promising input locations for evaluation. When dealing with composite-structured functions, such as f=g o h, evaluating a specific location x yields observations of both the final outcome f(x) = g(h(x)) as well as the intermediate output(s) h(x). Previous research has shown that integrating information from these intermediate outputs can enhance BO performance substantially. However, existing methods struggle if the outputs h(x) are high-dimensional. Many relevant problems fall into this setting, including in the context of generative AI, molecular design, or robotics. To effectively tackle these challenges, we introduce Joint Composite Latent Space Bayesian Optimization (JoCo), a novel framework that jointly trains neural network encoders and probabilistic models to adaptively compress high-dimensional input and output spaces into manageable latent representations. This enables viable BO on these compressed representations, allowing JoCo to outperform other state-of-the-art methods in high-dimensional BO on a wide variety of simulated and real-world problems.
title Joint Composite Latent Space Bayesian Optimization
topic Machine Learning
url https://arxiv.org/abs/2311.02213