Establishing Linear Surrogate Regret Bounds for Convex Smooth Losses via Convolutional Fenchel–Young Losses
NeurIPSSpotlight2025
TL;DR
Surrogate regret bounds, also known as excess risk bounds, bridge the gap between the convergence rates of surrogate and target losses…
Opening excerpt from the authors’ abstract. source
Read the paper
Topics
convergence regret
← All NeurIPS 2025 Spotlight papers · Browse the whole archive