Enabling Optimal Decisions in Rehearsal Learning under CARE Condition

Wen-Bo Du, Hao-Yi Lei, Lue Tao, Tian-Zuo Wang, Zhi-Hua Zhou
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:14536-14561, 2025.

Abstract

In the field of machine learning (ML), an essential type of decision-related problem is known as AUF (Avoiding Undesired Future): if an ML model predicts an undesired outcome, how can decisions be made to prevent it? Recently, a novel framework called rehearsal learning has been proposed to address the AUF problem. Despite its utility in modeling uncertainty for decision-making, it remains unclear under what conditions and how optimal actions that maximize the AUF probability can be identified. In this paper, we propose CARE (CAnonical REctangle), a condition under which the maximum AUF probability can be achieved. Under the CARE condition, we present a projection-Newton algorithm to select actions and prove that the algorithm achieves superlinear convergence to the optimal one. Besides, we provide a generalization method for adopting the algorithm to AUF scenarios beyond the CARE condition. Finally, we demonstrate that a closed-form solution exists when the outcome is a singleton variable, substantially reducing the time complexity of decision-making. Experiments validate the effectiveness and efficiency of our method.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-du25b, title = {Enabling Optimal Decisions in Rehearsal Learning under {CARE} Condition}, author = {Du, Wen-Bo and Lei, Hao-Yi and Tao, Lue and Wang, Tian-Zuo and Zhou, Zhi-Hua}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {14536--14561}, 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/du25b/du25b.pdf}, url = {https://proceedings.mlr.press/v267/du25b.html}, abstract = {In the field of machine learning (ML), an essential type of decision-related problem is known as AUF (Avoiding Undesired Future): if an ML model predicts an undesired outcome, how can decisions be made to prevent it? Recently, a novel framework called rehearsal learning has been proposed to address the AUF problem. Despite its utility in modeling uncertainty for decision-making, it remains unclear under what conditions and how optimal actions that maximize the AUF probability can be identified. In this paper, we propose CARE (CAnonical REctangle), a condition under which the maximum AUF probability can be achieved. Under the CARE condition, we present a projection-Newton algorithm to select actions and prove that the algorithm achieves superlinear convergence to the optimal one. Besides, we provide a generalization method for adopting the algorithm to AUF scenarios beyond the CARE condition. Finally, we demonstrate that a closed-form solution exists when the outcome is a singleton variable, substantially reducing the time complexity of decision-making. Experiments validate the effectiveness and efficiency of our method.} }
Endnote
%0 Conference Paper %T Enabling Optimal Decisions in Rehearsal Learning under CARE Condition %A Wen-Bo Du %A Hao-Yi Lei %A Lue Tao %A Tian-Zuo Wang %A Zhi-Hua Zhou %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-du25b %I PMLR %P 14536--14561 %U https://proceedings.mlr.press/v267/du25b.html %V 267 %X In the field of machine learning (ML), an essential type of decision-related problem is known as AUF (Avoiding Undesired Future): if an ML model predicts an undesired outcome, how can decisions be made to prevent it? Recently, a novel framework called rehearsal learning has been proposed to address the AUF problem. Despite its utility in modeling uncertainty for decision-making, it remains unclear under what conditions and how optimal actions that maximize the AUF probability can be identified. In this paper, we propose CARE (CAnonical REctangle), a condition under which the maximum AUF probability can be achieved. Under the CARE condition, we present a projection-Newton algorithm to select actions and prove that the algorithm achieves superlinear convergence to the optimal one. Besides, we provide a generalization method for adopting the algorithm to AUF scenarios beyond the CARE condition. Finally, we demonstrate that a closed-form solution exists when the outcome is a singleton variable, substantially reducing the time complexity of decision-making. Experiments validate the effectiveness and efficiency of our method.
APA
Du, W., Lei, H., Tao, L., Wang, T. & Zhou, Z.. (2025). Enabling Optimal Decisions in Rehearsal Learning under CARE Condition. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:14536-14561 Available from https://proceedings.mlr.press/v267/du25b.html.

Related Material