ACE: Adapting sampling for Counterfactual Explanations

Margarita A. Guerrero, Cristian R. Rojas
Proceedings of The 8th Annual Learning for Dynamics and Control Conference, PMLR 331:242-264, 2026.

Abstract

Counterfactual Explanations (CFEs) interpret machine learning models by identifying the smallest change to input features needed to change the model’s prediction to a desired output. For classification tasks, CFEs determine how close a given sample is to the decision boundary of a trained classifier. Existing methods are often sample-inefficient, requiring numerous evaluations of a black-box model, which can be impractical when access to the model is limited. We propose Adaptive sampling for Counterfactual Explanations (ACE), a sample-efficient algorithm combining Bayesian estimation and stochastic optimization to approximate the decision boundary with fewer queries. By prioritizing informative points, ACE minimizes evaluations while generating accurate and feasible CFEs. Across benchmarks, ACE delivers higher query efficiency than state-of-the-art methods, yielding minimal changes, and demonstrates effectiveness in a control-tuning application.

Cite this Paper

BibTeX
@InProceedings{pmlr-v331-guerrero26a, title = {ACE: Adapting sampling for Counterfactual Explanations}, author = {Guerrero, Margarita A. and Rojas, Cristian R.}, booktitle = {Proceedings of The 8th Annual Learning for Dynamics and Control Conference}, pages = {242--264}, year = {2026}, editor = {Sukhatme, Gaurav and Lindemann, Lars and Tu, Stephen and Wierman, Adam and Atanasov, Nikolay}, volume = {331}, series = {Proceedings of Machine Learning Research}, month = {17--19 Jun}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v331/main/assets/guerrero26a/guerrero26a.pdf}, url = {https://proceedings.mlr.press/v331/guerrero26a.html}, abstract = {Counterfactual Explanations (CFEs) interpret machine learning models by identifying the smallest change to input features needed to change the model’s prediction to a desired output. For classification tasks, CFEs determine how close a given sample is to the decision boundary of a trained classifier. Existing methods are often sample-inefficient, requiring numerous evaluations of a black-box model, which can be impractical when access to the model is limited. We propose Adaptive sampling for Counterfactual Explanations (ACE), a sample-efficient algorithm combining Bayesian estimation and stochastic optimization to approximate the decision boundary with fewer queries. By prioritizing informative points, ACE minimizes evaluations while generating accurate and feasible CFEs. Across benchmarks, ACE delivers higher query efficiency than state-of-the-art methods, yielding minimal changes, and demonstrates effectiveness in a control-tuning application.} }
Endnote
%0 Conference Paper %T ACE: Adapting sampling for Counterfactual Explanations %A Margarita A. Guerrero %A Cristian R. Rojas %B Proceedings of The 8th Annual Learning for Dynamics and Control Conference %C Proceedings of Machine Learning Research %D 2026 %E Gaurav Sukhatme %E Lars Lindemann %E Stephen Tu %E Adam Wierman %E Nikolay Atanasov %F pmlr-v331-guerrero26a %I PMLR %P 242--264 %U https://proceedings.mlr.press/v331/guerrero26a.html %V 331 %X Counterfactual Explanations (CFEs) interpret machine learning models by identifying the smallest change to input features needed to change the model’s prediction to a desired output. For classification tasks, CFEs determine how close a given sample is to the decision boundary of a trained classifier. Existing methods are often sample-inefficient, requiring numerous evaluations of a black-box model, which can be impractical when access to the model is limited. We propose Adaptive sampling for Counterfactual Explanations (ACE), a sample-efficient algorithm combining Bayesian estimation and stochastic optimization to approximate the decision boundary with fewer queries. By prioritizing informative points, ACE minimizes evaluations while generating accurate and feasible CFEs. Across benchmarks, ACE delivers higher query efficiency than state-of-the-art methods, yielding minimal changes, and demonstrates effectiveness in a control-tuning application.
APA
Guerrero, M.A. & Rojas, C.R.. (2026). ACE: Adapting sampling for Counterfactual Explanations. Proceedings of The 8th Annual Learning for Dynamics and Control Conference, in Proceedings of Machine Learning Research 331:242-264 Available from https://proceedings.mlr.press/v331/guerrero26a.html.

Related Material