3 papers
cs.LG2025
Simplifying Adversarially Robust PAC Learning with Tolerance
Hassan Ashtiani, Vinayak Pathak, Ruth Urner
Adversarially robust PAC learning has proved to be challenging, with the currently best known learners [Montasser et al., 2021a] relying on improper methods based on intricate comp…
cs.LG2025
On the Computability of Multiclass PAC Learning
Pascale Gourdeau, Tosca Lechner, Ruth Urner
We study the problem of computable multiclass learnability within the Probably Approximately Correct (PAC) learning framework of Valiant (1984). In the recently introduced computab…
cs.LG2024
Calibration through the Lens of Interpretability
Alireza Torabian, Ruth Urner
Calibration is a frequently invoked concept when useful label probability estimates are required on top of classification accuracy. A calibrated model is a function whose values co…