12 citations · 26 across the 23 of their papers we have counts for
3 papers · 1 filter
Black-Box Uniform Stability for Non-Euclidean Empirical Risk Minimization
Simon Vary, David Martínez-Rubio, Patrick Rebeschini
We study first-order algorithms that are uniformly stable for empirical risk minimization (ERM) problems that are convex and smooth with respect to -norms, . We propos…
Meta-Learning Objectives for Preference Optimization
Carlo Alfano, Silvia Sapora, Jakob Nicolaus Foerster +2
Evaluating preference optimization (PO) algorithms on LLM alignment is a challenging task that presents prohibitive costs, noise, and several variables like model size and hyper-pa…
Robust Gradient Descent for Phase Retrieval
Alex Buna, Patrick Rebeschini
Recent progress in robust statistical learning has mainly tackled convex problems, like mean estimation or linear regression, with non-convex challenges receiving less attention. P…