Unified framework for entropy search and expected improvement in Bayesian optimization
(2025)- Abstract
- Bayesian optimization is a widely used method for optimizing expensive black-box functions, with Expected Improvement being one of the most commonly used acquisition functions. In contrast, information-theoretic acquisition functions aim to reduce uncertainty about the function's optimum and are often considered fundamentally distinct from EI. In this work, we challenge this prevailing perspective by introducing a unified theoretical framework, Variational Entropy Search, which reveals that EI and information-theoretic acquisition functions are more closely related than previously recognized. We demonstrate that EI can be interpreted as a variational inference approximation of the popular information-theoretic acquisition function, named... (More)
- Bayesian optimization is a widely used method for optimizing expensive black-box functions, with Expected Improvement being one of the most commonly used acquisition functions. In contrast, information-theoretic acquisition functions aim to reduce uncertainty about the function's optimum and are often considered fundamentally distinct from EI. In this work, we challenge this prevailing perspective by introducing a unified theoretical framework, Variational Entropy Search, which reveals that EI and information-theoretic acquisition functions are more closely related than previously recognized. We demonstrate that EI can be interpreted as a variational inference approximation of the popular information-theoretic acquisition function, named Max-value Entropy Search. Building on this insight, we propose VES-Gamma, a novel acquisition function that balances the strengths of EI and MES. Extensive empirical evaluations across both low- and high-dimensional synthetic and real-world benchmarks demonstrate that VES-Gamma is competitive with state-of-the-art acquisition functions and in many cases outperforms EI and MES. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/4e1e1448-f73d-44cc-a995-027c7bbe4a38
- author
- Cheng, Nuojin
; Papenmeier, Leonard
LU
; Becker, Stephen and Nardi, Luigi LU
- organization
- publishing date
- 2025
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- in press
- subject
- host publication
- Forty-Second International Conference on Machine Learning
- pages
- 13 pages
- language
- English
- LU publication?
- yes
- id
- 4e1e1448-f73d-44cc-a995-027c7bbe4a38
- alternative location
- https://arxiv.org/abs/2501.18756
- date added to LUP
- 2025-05-07 15:08:36
- date last changed
- 2025-05-15 11:05:12
@inproceedings{4e1e1448-f73d-44cc-a995-027c7bbe4a38, abstract = {{Bayesian optimization is a widely used method for optimizing expensive black-box functions, with Expected Improvement being one of the most commonly used acquisition functions. In contrast, information-theoretic acquisition functions aim to reduce uncertainty about the function's optimum and are often considered fundamentally distinct from EI. In this work, we challenge this prevailing perspective by introducing a unified theoretical framework, Variational Entropy Search, which reveals that EI and information-theoretic acquisition functions are more closely related than previously recognized. We demonstrate that EI can be interpreted as a variational inference approximation of the popular information-theoretic acquisition function, named Max-value Entropy Search. Building on this insight, we propose VES-Gamma, a novel acquisition function that balances the strengths of EI and MES. Extensive empirical evaluations across both low- and high-dimensional synthetic and real-world benchmarks demonstrate that VES-Gamma is competitive with state-of-the-art acquisition functions and in many cases outperforms EI and MES.}}, author = {{Cheng, Nuojin and Papenmeier, Leonard and Becker, Stephen and Nardi, Luigi}}, booktitle = {{Forty-Second International Conference on Machine Learning}}, language = {{eng}}, title = {{Unified framework for entropy search and expected improvement in Bayesian optimization}}, url = {{https://arxiv.org/abs/2501.18756}}, year = {{2025}}, }