Jul 2026
Breaking the T3/4 Barrier for Regret Minimization With Bi-Dimensional CDFs
An algorithm achieving regret $\widetilde{\mathcal{O}}(T^{7/10})$ is designed, improving over the previous best-known bound of $\widetilde{\mathcal{O}}(T^{3/4})$ and showing that the curse of dimensionality can be at least partially lifted for this class of objectives.
Matteo Castiglioni, Anna Lunghi, A. Marchesi
· arXiv.org · 0 citations