Improved Strongly Adaptive Online Learning using Coin Betting

10/14/2016
by   Kwang-Sung Jun, et al.
0

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 √((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.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset