Blair Bilodeau, Dylan J. Foster, Daniel M. Roy 0001. Tight Bounds on Minimax Regret under Logarithmic Loss via Self-Concordance. In Proceedings of the 37th International Conference on Machine Learning, ICML 2020, 13-18 July 2020, Virtual Event. Volume 119 of Proceedings of Machine Learning Research, pages 919-929, PMLR, 2020. [doi]
Abstract is missing.