Risk Seeking Bayesian Optimization under Uncertainty for Obtaining Extremum

Shogo Iwazaki, Tomohiko Tanabe, Mitsuru Irie, Shion Takeno, Yu Inatsu
Proceedings of The 27th International Conference on Artificial Intelligence and Statistics, PMLR 238:1252-1260, 2024.

Abstract

Real-world black-box optimization tasks often focus on obtaining the best reward, which includes an intrinsic random quantity from uncontrollable environmental factors. For this problem, we formulate a novel risk-seeking optimization problem whose aim is to obtain the best possible reward within a fixed budget under uncontrollable factors. We consider two settings: (1) environmental model setting for the case that we can observe uncontrollable environmental variables that affect the observation as the input of a target function, and (2) heteroscedastic model setting for the case that any uncontrollable variables cannot be observed. We propose a novel Bayesian optimization method called kernel explore-then-commit (kernel-ETC) and provide the regret upper bound for both settings. We demonstrate the effectiveness of kernel-ETC through several numerical experiments, including the hyperparameter tuning task and the simulation function derived from polymer synthesis real data.

Cite this Paper

BibTeX
@InProceedings{pmlr-v238-iwazaki24a, title = { Risk Seeking {B}ayesian Optimization under Uncertainty for Obtaining Extremum }, author = {Iwazaki, Shogo and Tanabe, Tomohiko and Irie, Mitsuru and Takeno, Shion and Inatsu, Yu}, booktitle = {Proceedings of The 27th International Conference on Artificial Intelligence and Statistics}, pages = {1252--1260}, year = {2024}, editor = {Dasgupta, Sanjoy and Mandt, Stephan and Li, Yingzhen}, volume = {238}, series = {Proceedings of Machine Learning Research}, month = {02--04 May}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v238/iwazaki24a/iwazaki24a.pdf}, url = {https://proceedings.mlr.press/v238/iwazaki24a.html}, abstract = { Real-world black-box optimization tasks often focus on obtaining the best reward, which includes an intrinsic random quantity from uncontrollable environmental factors. For this problem, we formulate a novel risk-seeking optimization problem whose aim is to obtain the best possible reward within a fixed budget under uncontrollable factors. We consider two settings: (1) environmental model setting for the case that we can observe uncontrollable environmental variables that affect the observation as the input of a target function, and (2) heteroscedastic model setting for the case that any uncontrollable variables cannot be observed. We propose a novel Bayesian optimization method called kernel explore-then-commit (kernel-ETC) and provide the regret upper bound for both settings. We demonstrate the effectiveness of kernel-ETC through several numerical experiments, including the hyperparameter tuning task and the simulation function derived from polymer synthesis real data. } }
Endnote
%0 Conference Paper %T Risk Seeking Bayesian Optimization under Uncertainty for Obtaining Extremum %A Shogo Iwazaki %A Tomohiko Tanabe %A Mitsuru Irie %A Shion Takeno %A Yu Inatsu %B Proceedings of The 27th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2024 %E Sanjoy Dasgupta %E Stephan Mandt %E Yingzhen Li %F pmlr-v238-iwazaki24a %I PMLR %P 1252--1260 %U https://proceedings.mlr.press/v238/iwazaki24a.html %V 238 %X Real-world black-box optimization tasks often focus on obtaining the best reward, which includes an intrinsic random quantity from uncontrollable environmental factors. For this problem, we formulate a novel risk-seeking optimization problem whose aim is to obtain the best possible reward within a fixed budget under uncontrollable factors. We consider two settings: (1) environmental model setting for the case that we can observe uncontrollable environmental variables that affect the observation as the input of a target function, and (2) heteroscedastic model setting for the case that any uncontrollable variables cannot be observed. We propose a novel Bayesian optimization method called kernel explore-then-commit (kernel-ETC) and provide the regret upper bound for both settings. We demonstrate the effectiveness of kernel-ETC through several numerical experiments, including the hyperparameter tuning task and the simulation function derived from polymer synthesis real data.
APA
Iwazaki, S., Tanabe, T., Irie, M., Takeno, S. & Inatsu, Y.. (2024). Risk Seeking Bayesian Optimization under Uncertainty for Obtaining Extremum . Proceedings of The 27th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 238:1252-1260 Available from https://proceedings.mlr.press/v238/iwazaki24a.html.

Related Material