3 papers
cs.LG2026
The Sample Complexity of Distributionally Robust PAC Learning under Cressie--Read Divergences
Elad Aigner-Horev, Daniel Rosenberg, Roi Weiss
We study distributionally robust PAC learning for the ---loss, where adversarial perturbations of the data distribution are constrained by a Cressie--Read divergence of order…
math.PR2025
Resilience of Rademacher chaos of low degree
Elad Aigner-Horev, Daniel Rosenberg, Roi Weiss
The {\em resilience} of a Rademacher chaos is the maximum number of adversarial sign-flips that the chaos can sustain without having its largest atom probability significantly alte…
math.ST2025
The Empirical Mean is Minimax Optimal for Local Glivenko-Cantelli
Doron Cohen, Aryeh Kontorovich, Roi Weiss
We revisit the recently introduced Local Glivenko-Cantelli setting, which studies distribution-dependent uniform convergence rates of the Empirical Mean Estimator (EME). In this wo…