No-Regret Bayesian Optimization with Stochastic Observation Failures

Shogo Iwazaki, Tomohiko Tanabe, Mitsuru Irie, Shion Takeno, Kota Matsui, Yu Inatsu
Proceedings of The 28th International Conference on Artificial Intelligence and Statistics, PMLR 258:415-423, 2025.

Abstract

We study Bayesian optimization problems where observation of the objective function fails stochastically, e.g., synthesis failures in materials development. For this problem, although several heuristic methods have been proposed, they do not have theoretical guarantees and sometimes deteriorate in practice. We propose two algorithms that have a trade-off relation between regret bounds and practical performance. The first one is the first no-regret algorithm for this problem. The second one shows superior practical performance; however, we need some modification of the algorithm to obtain a no-regret guarantee, which is slightly worse than the first one. We demonstrate the effectiveness of our methods in numerical experiments, including the simulation function motivated by quasi-crystal synthesis.

Cite this Paper

BibTeX
@InProceedings{pmlr-v258-iwazaki25b, title = {No-Regret Bayesian Optimization with Stochastic Observation Failures}, author = {Iwazaki, Shogo and Tanabe, Tomohiko and Irie, Mitsuru and Takeno, Shion and Matsui, Kota and Inatsu, Yu}, booktitle = {Proceedings of The 28th International Conference on Artificial Intelligence and Statistics}, pages = {415--423}, year = {2025}, editor = {Li, Yingzhen and Mandt, Stephan and Agrawal, Shipra and Khan, Emtiyaz}, volume = {258}, series = {Proceedings of Machine Learning Research}, month = {03--05 May}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v258/main/assets/iwazaki25b/iwazaki25b.pdf}, url = {https://proceedings.mlr.press/v258/iwazaki25b.html}, abstract = {We study Bayesian optimization problems where observation of the objective function fails stochastically, e.g., synthesis failures in materials development. For this problem, although several heuristic methods have been proposed, they do not have theoretical guarantees and sometimes deteriorate in practice. We propose two algorithms that have a trade-off relation between regret bounds and practical performance. The first one is the first no-regret algorithm for this problem. The second one shows superior practical performance; however, we need some modification of the algorithm to obtain a no-regret guarantee, which is slightly worse than the first one. We demonstrate the effectiveness of our methods in numerical experiments, including the simulation function motivated by quasi-crystal synthesis.} }
Endnote
%0 Conference Paper %T No-Regret Bayesian Optimization with Stochastic Observation Failures %A Shogo Iwazaki %A Tomohiko Tanabe %A Mitsuru Irie %A Shion Takeno %A Kota Matsui %A Yu Inatsu %B Proceedings of The 28th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2025 %E Yingzhen Li %E Stephan Mandt %E Shipra Agrawal %E Emtiyaz Khan %F pmlr-v258-iwazaki25b %I PMLR %P 415--423 %U https://proceedings.mlr.press/v258/iwazaki25b.html %V 258 %X We study Bayesian optimization problems where observation of the objective function fails stochastically, e.g., synthesis failures in materials development. For this problem, although several heuristic methods have been proposed, they do not have theoretical guarantees and sometimes deteriorate in practice. We propose two algorithms that have a trade-off relation between regret bounds and practical performance. The first one is the first no-regret algorithm for this problem. The second one shows superior practical performance; however, we need some modification of the algorithm to obtain a no-regret guarantee, which is slightly worse than the first one. We demonstrate the effectiveness of our methods in numerical experiments, including the simulation function motivated by quasi-crystal synthesis.
APA
Iwazaki, S., Tanabe, T., Irie, M., Takeno, S., Matsui, K. & Inatsu, Y.. (2025). No-Regret Bayesian Optimization with Stochastic Observation Failures. Proceedings of The 28th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 258:415-423 Available from https://proceedings.mlr.press/v258/iwazaki25b.html.

Related Material