This paper describes a new parameter-free online learning algorithm for changing environments. In comparing against algorithms with the same time complexity as ours, we obtain a strongly adaptive regret bound that is a factor of at least √log(T) better, where T is the time horizon. Empirical results show that our algorithm outperforms state-of-the-art methods in learning with expert advice and metric learning scenarios.
|Original language||English (US)|
|Title of host publication||Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, AISTATS 2017|
|State||Published - Jan 1 2017|