Pareto-Optimal Probabilistic Explanations: Balancing Cognitive Constraints and User Preferences

Louenas Bounia
Proceedings of the 42nd Conference on Uncertainty in Artificial Intelligence, PMLR 337:658-688, 2026.

Abstract

Machine learning classifiers deployed in critical domains require comprehensible explanations. Abductive explanations identify minimal feature sets guaranteeing a decision but suffer from two limitations: exceeding human cognitive limits and ignoring user preferences (actionability, fairness, cost). Probabilistic explanations reduce size via controlled error, while preferred explanations integrate preferences; however, these approaches remain disjoint. We introduce the first framework unifying these paradigms: preferred probabilistic explanations balancing cognitive constraints, probabilistic accuracy, and user preferences. We formulate the problem via weighted scalarization **WPPE** and Pareto optimization PPPE, prove **NP**-hardness for decision trees, and exploit supermodularity to establish approximation guarantees. We propose three complementary algorithms: weighted greedy descent **WGD** with ratio $(e^{p_w}-1)/p_w$, Pareto frontier enumeration **PFE** for interactive exploration of non-dominated trade-offs, and lexicographic stratified algorithm **LSA** for strict ordinal preferences. Our framework enables rigorous navigation of the Pareto-optimal trade-off space between cognitive limits and user preferences.

Cite this Paper

BibTeX
@InProceedings{pmlr-v337-bounia26a, title = {Pareto-Optimal Probabilistic Explanations: Balancing Cognitive Constraints and User Preferences}, author = {Bounia, Louenas}, booktitle = {Proceedings of the 42nd Conference on Uncertainty in Artificial Intelligence}, pages = {658--688}, year = {2026}, editor = {Perković, Emilija and Malinsky, Daniel}, volume = {337}, series = {Proceedings of Machine Learning Research}, month = {17--21 Aug}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v337/main/assets/bounia26a/bounia26a.pdf}, url = {https://proceedings.mlr.press/v337/bounia26a.html}, abstract = {Machine learning classifiers deployed in critical domains require comprehensible explanations. Abductive explanations identify minimal feature sets guaranteeing a decision but suffer from two limitations: exceeding human cognitive limits and ignoring user preferences (actionability, fairness, cost). Probabilistic explanations reduce size via controlled error, while preferred explanations integrate preferences; however, these approaches remain disjoint. We introduce the first framework unifying these paradigms: preferred probabilistic explanations balancing cognitive constraints, probabilistic accuracy, and user preferences. We formulate the problem via weighted scalarization **WPPE** and Pareto optimization PPPE, prove **NP**-hardness for decision trees, and exploit supermodularity to establish approximation guarantees. We propose three complementary algorithms: weighted greedy descent **WGD** with ratio $(e^{p_w}-1)/p_w$, Pareto frontier enumeration **PFE** for interactive exploration of non-dominated trade-offs, and lexicographic stratified algorithm **LSA** for strict ordinal preferences. Our framework enables rigorous navigation of the Pareto-optimal trade-off space between cognitive limits and user preferences.} }
Endnote
%0 Conference Paper %T Pareto-Optimal Probabilistic Explanations: Balancing Cognitive Constraints and User Preferences %A Louenas Bounia %B Proceedings of the 42nd Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2026 %E Emilija Perković %E Daniel Malinsky %F pmlr-v337-bounia26a %I PMLR %P 658--688 %U https://proceedings.mlr.press/v337/bounia26a.html %V 337 %X Machine learning classifiers deployed in critical domains require comprehensible explanations. Abductive explanations identify minimal feature sets guaranteeing a decision but suffer from two limitations: exceeding human cognitive limits and ignoring user preferences (actionability, fairness, cost). Probabilistic explanations reduce size via controlled error, while preferred explanations integrate preferences; however, these approaches remain disjoint. We introduce the first framework unifying these paradigms: preferred probabilistic explanations balancing cognitive constraints, probabilistic accuracy, and user preferences. We formulate the problem via weighted scalarization **WPPE** and Pareto optimization PPPE, prove **NP**-hardness for decision trees, and exploit supermodularity to establish approximation guarantees. We propose three complementary algorithms: weighted greedy descent **WGD** with ratio $(e^{p_w}-1)/p_w$, Pareto frontier enumeration **PFE** for interactive exploration of non-dominated trade-offs, and lexicographic stratified algorithm **LSA** for strict ordinal preferences. Our framework enables rigorous navigation of the Pareto-optimal trade-off space between cognitive limits and user preferences.
APA
Bounia, L.. (2026). Pareto-Optimal Probabilistic Explanations: Balancing Cognitive Constraints and User Preferences. Proceedings of the 42nd Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research 337:658-688 Available from https://proceedings.mlr.press/v337/bounia26a.html.

Related Material