No-regret $\mathrm{M}^\natural$-concave function maximization: Stochastic bandit algorithms and NP-hardness of adversarial full-information settingDec 1, 2024·Taihei Oki,Shinsaku Sakaue· 0 min read PDFTypeConference paperPublicationAdvances in Neural Information Processing Systems (NeurIPS)Last updated on Dec 1, 2024 ← Generalization bound and learning methods for data-driven projections in linear programming Dec 1, 2024Online structured prediction with Fenchel–Young losses and improved surrogate regret for online multiclass classification with logistic loss Jul 1, 2024 →