Home Page




Editorial Board

Proceedings (PMLR)

Transactions (TMLR)

Open Source Software




Frequently Asked Questions

Contact Us

RSS Feed

Online Learning via Sequential Complexities

Alexander Rakhlin, Karthik Sridharan, Ambuj Tewari; 16(6):155−186, 2015.


We consider the problem of sequential prediction and provide tools to study the minimax value of the associated game. Classical statistical learning theory provides several useful complexity measures to study learning with i.i.d. data. Our proposed sequential complexities can be seen as extensions of these measures to the sequential setting. The developed theory is shown to yield precise learning guarantees for the problem of sequential prediction. In particular, we show necessary and sufficient conditions for online learnability in the setting of supervised learning. Several examples show the utility of our framework: we can establish learnability without having to exhibit an explicit online learning algorithm.

© JMLR 2015. (edit, beta)