Causal Logistic Bandits with Counterfactual Fairness Constraints

Jiajun Chen, Jin Tian, Christopher John Quinn
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:9146-9175, 2025.

Abstract

Artificial intelligence will play a significant role in decision making in numerous aspects of society. Numerous fairness criteria have been proposed in the machine learning community, but there remains limited investigation into fairness as defined through specified attributes in a sequential decision-making framework. In this paper, we focus on causal logistic bandit problems where the learner seeks to make fair decisions, under a notion of fairness that accounts for counterfactual reasoning. We propose and analyze an algorithm by leveraging primal-dual optimization for constrained causal logistic bandits where the non-linear constraints are a priori unknown and must be learned in time. We obtain sub-linear regret guarantees with leading term similar to that for unconstrained logistic bandits (Lee et al., 2024) while guaranteeing sub-linear constraint violations. We show how to achieve zero cumulative constraint violations with a small increase in the regret bound.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-chen25bk, title = {Causal Logistic Bandits with Counterfactual Fairness Constraints}, author = {Chen, Jiajun and Tian, Jin and Quinn, Christopher John}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {9146--9175}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/chen25bk/chen25bk.pdf}, url = {https://proceedings.mlr.press/v267/chen25bk.html}, abstract = {Artificial intelligence will play a significant role in decision making in numerous aspects of society. Numerous fairness criteria have been proposed in the machine learning community, but there remains limited investigation into fairness as defined through specified attributes in a sequential decision-making framework. In this paper, we focus on causal logistic bandit problems where the learner seeks to make fair decisions, under a notion of fairness that accounts for counterfactual reasoning. We propose and analyze an algorithm by leveraging primal-dual optimization for constrained causal logistic bandits where the non-linear constraints are a priori unknown and must be learned in time. We obtain sub-linear regret guarantees with leading term similar to that for unconstrained logistic bandits (Lee et al., 2024) while guaranteeing sub-linear constraint violations. We show how to achieve zero cumulative constraint violations with a small increase in the regret bound.} }
Endnote
%0 Conference Paper %T Causal Logistic Bandits with Counterfactual Fairness Constraints %A Jiajun Chen %A Jin Tian %A Christopher John Quinn %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-chen25bk %I PMLR %P 9146--9175 %U https://proceedings.mlr.press/v267/chen25bk.html %V 267 %X Artificial intelligence will play a significant role in decision making in numerous aspects of society. Numerous fairness criteria have been proposed in the machine learning community, but there remains limited investigation into fairness as defined through specified attributes in a sequential decision-making framework. In this paper, we focus on causal logistic bandit problems where the learner seeks to make fair decisions, under a notion of fairness that accounts for counterfactual reasoning. We propose and analyze an algorithm by leveraging primal-dual optimization for constrained causal logistic bandits where the non-linear constraints are a priori unknown and must be learned in time. We obtain sub-linear regret guarantees with leading term similar to that for unconstrained logistic bandits (Lee et al., 2024) while guaranteeing sub-linear constraint violations. We show how to achieve zero cumulative constraint violations with a small increase in the regret bound.
APA
Chen, J., Tian, J. & Quinn, C.J.. (2025). Causal Logistic Bandits with Counterfactual Fairness Constraints. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:9146-9175 Available from https://proceedings.mlr.press/v267/chen25bk.html.

Related Material