





















Abstract:The growing use of Machine Learning (ML) tools comes with critical challenges, such as limited model explainability. We propose a global explainability framework that leverages Optimal Transport and Distributionally Robust Optimization to analyze how ML algorithms respond to constrained data perturbations. Our approach enforces constraints on feature-level statistics (e.g., brightness, age distribution), generating realistic perturbations that preserve semantic structure. We provide a model-agnostic diagnostic bench that applies to both tabular and image domains with solid theoretical guarantees. We validate the approach on real-world datasets providing interpretable robustness diagnostics that complement standard evaluation and fairness auditing tools.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2603.15867 [cs.LG] |
| (or arXiv:2603.15867v2 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2603.15867 arXiv-issued DOI via DataCite |
From: Adriana Laurindo Monteiro [view email]
[v1]
Mon, 16 Mar 2026 19:56:57 UTC (342 KB)
[v2]
Wed, 22 Apr 2026 14:08:11 UTC (1,113 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理,仅供阅读参考。 原文来自 — 版权归原作者所有。