Exponential Smoothing for Off-Policy Learning

Imad Aouali, Victor-Emmanuel Brunel, David Rohde, Anna Korba
Proceedings of the 40th International Conference on Machine Learning, PMLR 202:984-1017, 2023.

Abstract

Off-policy learning (OPL) aims at finding improved policies from logged bandit data, often by minimizing the inverse propensity scoring (IPS) estimator of the risk. In this work, we investigate a smooth regularization for IPS, for which we derive a two-sided PAC-Bayes generalization bound. The bound is tractable, scalable, interpretable and provides learning certificates. In particular, it is also valid for standard IPS without making the assumption that the importance weights are bounded. We demonstrate the relevance of our approach and its favorable performance through a set of learning tasks. Since our bound holds for standard IPS, we are able to provide insight into when regularizing IPS is useful. Namely, we identify cases where regularization might not be needed. This goes against the belief that, in practice, clipped IPS often enjoys favorable performance than standard IPS in OPL.

Cite this Paper

BibTeX
@InProceedings{pmlr-v202-aouali23a, title = {Exponential Smoothing for Off-Policy Learning}, author = {Aouali, Imad and Brunel, Victor-Emmanuel and Rohde, David and Korba, Anna}, booktitle = {Proceedings of the 40th International Conference on Machine Learning}, pages = {984--1017}, year = {2023}, editor = {Krause, Andreas and Brunskill, Emma and Cho, Kyunghyun and Engelhardt, Barbara and Sabato, Sivan and Scarlett, Jonathan}, volume = {202}, series = {Proceedings of Machine Learning Research}, month = {23--29 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v202/aouali23a/aouali23a.pdf}, url = {https://proceedings.mlr.press/v202/aouali23a.html}, abstract = {Off-policy learning (OPL) aims at finding improved policies from logged bandit data, often by minimizing the inverse propensity scoring (IPS) estimator of the risk. In this work, we investigate a smooth regularization for IPS, for which we derive a two-sided PAC-Bayes generalization bound. The bound is tractable, scalable, interpretable and provides learning certificates. In particular, it is also valid for standard IPS without making the assumption that the importance weights are bounded. We demonstrate the relevance of our approach and its favorable performance through a set of learning tasks. Since our bound holds for standard IPS, we are able to provide insight into when regularizing IPS is useful. Namely, we identify cases where regularization might not be needed. This goes against the belief that, in practice, clipped IPS often enjoys favorable performance than standard IPS in OPL.} }
Endnote
%0 Conference Paper %T Exponential Smoothing for Off-Policy Learning %A Imad Aouali %A Victor-Emmanuel Brunel %A David Rohde %A Anna Korba %B Proceedings of the 40th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2023 %E Andreas Krause %E Emma Brunskill %E Kyunghyun Cho %E Barbara Engelhardt %E Sivan Sabato %E Jonathan Scarlett %F pmlr-v202-aouali23a %I PMLR %P 984--1017 %U https://proceedings.mlr.press/v202/aouali23a.html %V 202 %X Off-policy learning (OPL) aims at finding improved policies from logged bandit data, often by minimizing the inverse propensity scoring (IPS) estimator of the risk. In this work, we investigate a smooth regularization for IPS, for which we derive a two-sided PAC-Bayes generalization bound. The bound is tractable, scalable, interpretable and provides learning certificates. In particular, it is also valid for standard IPS without making the assumption that the importance weights are bounded. We demonstrate the relevance of our approach and its favorable performance through a set of learning tasks. Since our bound holds for standard IPS, we are able to provide insight into when regularizing IPS is useful. Namely, we identify cases where regularization might not be needed. This goes against the belief that, in practice, clipped IPS often enjoys favorable performance than standard IPS in OPL.
APA
Aouali, I., Brunel, V., Rohde, D. & Korba, A.. (2023). Exponential Smoothing for Off-Policy Learning. Proceedings of the 40th International Conference on Machine Learning, in Proceedings of Machine Learning Research 202:984-1017 Available from https://proceedings.mlr.press/v202/aouali23a.html.

Related Material