Dimension-Free Exponentiated Gradient
| 
51 | 
34 | 
0
Abstract
I present a new online learning algorithm that extends the exponentiated gradient framework to infinite dimensional spaces. My analysis shows that the algorithm is implicitly able to estimate the L2 norm of the unknown competitor, U , achieving a regret bound of the order of 
instead of the standard 
achievable without knowing U . For this analysis, I introduce novel tools for algorithms with time-varying regularizers, through the use of local smoothness. p Through a lower bound, I also show that the algorithm is optimal up to 
term for linear and Lipschitz losses.
还没有评论，说两句吧！
热门资源
Learning to Predi...
Much of model-based reinforcement learning invo...
Stratified Strate...
In this paper we introduce Stratified Strategy ...
The Variational S...
Unlike traditional images which do not offer in...
A Mathematical Mo...
Direct democracy, where each voter casts one vo...
Rating-Boosted La...
The performance of a recommendation system reli...
智能在线
400-630-6780
聆听.建议反馈
E-mail: support@tusaishared.com
资源分类
