2 papers
cs.LG2026
Smoothness-Based Derandomization of PAC-Bayes Bounds
Alexandre Lemire Paquin, Brahim Chaib-Draa, Philippe Giguère
We study PAC-Bayes derandomization for smooth loss functions. Our goal is to obtain generalization bounds that hold with high probability for deterministic predictors by exploiting…
cs.LG2026
Symmetrization of Loss Functions for Robust Training of Neural Networks in the Presence of Noisy Labels
Alexandre Lemire Paquin, Brahim Chaib-Draa, Philippe Giguère
Labeling a training set is often expensive and susceptible to errors, making the design of robust loss functions for label noise an important problem. The symmetry condition provid…