Online structured prediction with Fenchel–Young losses and improved surrogate regret for online multiclass classification with logistic lossJul 1, 2024·Shinsaku Sakaue,Han Bao,Taira Tsuchiya,Taihei Oki· 0 min read PDF SlidesTypeConference paperPublicationConference on Learning Theory (COLT)Last updated on Jul 1, 2024 ← No-regret $\mathrm{M}^\natural$-concave function maximization: Stochastic bandit algorithms and NP-hardness of adversarial full-information setting Dec 1, 2024Faster discrete convex function minimization with predictions: The $\mathrm{M}$-convex case Dec 1, 2023 →
