Collaborative Bayesian Optimization with Fair Regret

Rachael Hwee Ling Sim, Yehong Zhang, Bryan Kian Hsiang Low, Patrick Jaillet
Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9691-9701, 2021.

Abstract

Bayesian optimization (BO) is a popular tool for optimizing complex and costly-to-evaluate black-box objective functions. To further reduce the number of function evaluations, any party performing BO may be interested to collaborate with others to optimize the same objective function concurrently. To do this, existing BO algorithms have considered optimizing a batch of input queries in parallel and provided theoretical bounds on their cumulative regret reflecting inefficiency. However, when the objective function values are correlated with real-world rewards (e.g., money), parties may be hesitant to collaborate if they risk incurring larger cumulative regret (i.e., smaller real-world reward) than others. This paper shows that fairness and efficiency are both necessary for the collaborative BO setting. Inspired by social welfare concepts from economics, we propose a new notion of regret capturing these properties and a collaborative BO algorithm whose convergence rate can be theoretically guaranteed by bounding the new regret, both of which share an adjustable parameter for trading off between fairness vs. efficiency. We empirically demonstrate the benefits (e.g., increased fairness) of our algorithm using synthetic and real-world datasets.

Cite this Paper

BibTeX
@InProceedings{pmlr-v139-sim21b, title = {Collaborative Bayesian Optimization with Fair Regret}, author = {Sim, Rachael Hwee Ling and Zhang, Yehong and Low, Bryan Kian Hsiang and Jaillet, Patrick}, booktitle = {Proceedings of the 38th International Conference on Machine Learning}, pages = {9691--9701}, year = {2021}, editor = {Meila, Marina and Zhang, Tong}, volume = {139}, series = {Proceedings of Machine Learning Research}, month = {18--24 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v139/sim21b/sim21b.pdf}, url = {https://proceedings.mlr.press/v139/sim21b.html}, abstract = {Bayesian optimization (BO) is a popular tool for optimizing complex and costly-to-evaluate black-box objective functions. To further reduce the number of function evaluations, any party performing BO may be interested to collaborate with others to optimize the same objective function concurrently. To do this, existing BO algorithms have considered optimizing a batch of input queries in parallel and provided theoretical bounds on their cumulative regret reflecting inefficiency. However, when the objective function values are correlated with real-world rewards (e.g., money), parties may be hesitant to collaborate if they risk incurring larger cumulative regret (i.e., smaller real-world reward) than others. This paper shows that fairness and efficiency are both necessary for the collaborative BO setting. Inspired by social welfare concepts from economics, we propose a new notion of regret capturing these properties and a collaborative BO algorithm whose convergence rate can be theoretically guaranteed by bounding the new regret, both of which share an adjustable parameter for trading off between fairness vs. efficiency. We empirically demonstrate the benefits (e.g., increased fairness) of our algorithm using synthetic and real-world datasets.} }
Endnote
%0 Conference Paper %T Collaborative Bayesian Optimization with Fair Regret %A Rachael Hwee Ling Sim %A Yehong Zhang %A Bryan Kian Hsiang Low %A Patrick Jaillet %B Proceedings of the 38th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2021 %E Marina Meila %E Tong Zhang %F pmlr-v139-sim21b %I PMLR %P 9691--9701 %U https://proceedings.mlr.press/v139/sim21b.html %V 139 %X Bayesian optimization (BO) is a popular tool for optimizing complex and costly-to-evaluate black-box objective functions. To further reduce the number of function evaluations, any party performing BO may be interested to collaborate with others to optimize the same objective function concurrently. To do this, existing BO algorithms have considered optimizing a batch of input queries in parallel and provided theoretical bounds on their cumulative regret reflecting inefficiency. However, when the objective function values are correlated with real-world rewards (e.g., money), parties may be hesitant to collaborate if they risk incurring larger cumulative regret (i.e., smaller real-world reward) than others. This paper shows that fairness and efficiency are both necessary for the collaborative BO setting. Inspired by social welfare concepts from economics, we propose a new notion of regret capturing these properties and a collaborative BO algorithm whose convergence rate can be theoretically guaranteed by bounding the new regret, both of which share an adjustable parameter for trading off between fairness vs. efficiency. We empirically demonstrate the benefits (e.g., increased fairness) of our algorithm using synthetic and real-world datasets.
APA
Sim, R.H.L., Zhang, Y., Low, B.K.H. & Jaillet, P.. (2021). Collaborative Bayesian Optimization with Fair Regret. Proceedings of the 38th International Conference on Machine Learning, in Proceedings of Machine Learning Research 139:9691-9701 Available from https://proceedings.mlr.press/v139/sim21b.html.

Related Material