Computing local-level variable importance (VI) is critical for understanding machine learning models. Local permutation-based VI metrics offer a simple yet powerful approach, measuring how much a model's output changes when perturbing its inputs. However, existing perturbation strategies often ignore feature dependence...
Yi-Xiao Wang, Srikar Katta, Jon Donnelly et al.· 0 citations
This narrative review examines how explainable artificial intelligence (XAI) may improve transparency and reliability by clarifying model behavior, revealing data dependencies, supporting error detection, and enabling informed human oversight.
MotiGen is a recipe for retrofitting pretrained symbolic music models to use new instruction prompts, which injects a musical motif as a structured prompt line, reinforces it with a scalar attention bias toward the motif tokens, and learns the association with a two-phase curriculum.
GRAVITree is presented, a novel dynamic-programming-with-bounds algorithm for learning the Rashomon set of falling trees under depth and branching constraints that can interpolate between rule lists and full decision trees, enabling user-desired model expressivity.
V. Babbar, Zachery Boner, Margo I. Seltzer et al.· 0 citations
This work introduces the first algorithm that exactly enumerates decision-tree Rashomon sets while exploiting the ordered structure of continuous features, and develops a relaxation for approximate enumeration and an anytime algorithm that progressively refines the set of candidate thresholds, producing increasingly de...
Zakk Heile, Hayden McTavish, Margo I. Seltzer et al.· 0 citations
This work introduces Multistage Defer Trees: a sequence of sparse decision trees that each make predictions for most samples, while deferring a small proportion to the next tree in the sequence or, ultimately, to a black box.
Zakk Heile, Hayden McTavish, Margo I. Seltzer et al.· arXiv.org· 1 citation
Machine learning surrogates based on neural operators have shown broad applicability in solving forward PDE problems. However, eigenvalue problems, in which an eigenparameter and one of several valid eigenmodes must be simultaneously solved, remain difficult because standard operator learning formulations assume a uniq...
Han Zhang, A. Ogren, C. Rudin et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.