1 code implementation • NeurIPS 2023 • Parnian Kassraie, Nicolas Emmenegger, Andreas Krause, Aldo Pacchiano
This allows us to develop ALEXP, which has an exponentially improved ($\log M$) dependence on $M$ for its regret.
no code implementations • 8 Mar 2021 • Nicolas Emmenegger, Rasmus Kyng, Ahad N. Zehmakan
We prove lower bounds for higher-order methods in smooth non-convex finite-sum optimization.