Non-uniform regret analysis
We study ways to incorporate prior expectations about the environment in the form of data-dependent luckiness guarantees.
-
Luckiness in multiscale online learning
Muriel Pérez-Ortiz, Wouter M. Koolen
In Advances in Neural Information Processing Systems (NeurIPS) 35, December 2022.
-
Lipschitz and comparator-norm adaptivity in online learning
Zakaria Mhammedi, Wouter M. Koolen
In Proceedings of the 33rd Annual Conference on Learning Theory (COLT), pages 2858–2887, July 2020.
-
MetaGrad: Multiple learning rates in online learning
Tim van Erven, Wouter M. Koolen
In Advances in Neural Information Processing Systems (NeurIPS) 29, pages 3666–3674, December 2016.
-
Second-order quantile methods for experts and combinatorial games
Wouter M. Koolen, Tim van Erven
In Proceedings of the 28th Annual Conference on Learning Theory (COLT), pages 1155–1175, June 2015.
-
The Pareto regret frontier
Wouter M. Koolen
In Advances in Neural Information Processing Systems (NeurIPS) 26, pages 863–871, December 2013.
