106 citations · 996 across the 72 of their papers we have counts for
4 papers · 1 filter
Fast Convergence of Regularized Learning in Games
Vasilis Syrgkanis, Alekh Agarwal, Haipeng Luo +1
We show that natural classes of regularized learning algorithms with a form of recency bias achieve faster convergence rates to approximate efficiency and to coarse correlated equi…
Online Gradient Boosting
Alina Beygelzimer, Elad Hazan, Satyen Kale +1
We extend the theory of boosting for regression problems to the online learning setting. Generalizing from the batch setting for boosting, the notion of a weak learning algorithm i…
Achieving All with No Parameters: Adaptive NormalHedge
Haipeng Luo, Robert E. Schapire
We study the classic online learning problem of predicting with expert advice, and propose a truly parameter-free and adaptive algorithm that achieves several objectives simultaneo…
Optimal and Adaptive Algorithms for Online Boosting
Alina Beygelzimer, Satyen Kale, Haipeng Luo
We study online boosting, the task of converting any weak online learner into a strong online learner. Based on a novel and natural definition of weak online learnability, we devel…