We present a new online learning algorithm in the selective sampling framework, where labels must be actively queried before they are revealed. We prove bounds on the regret of ou...
Online Boosting is an effective incremental learning method which can update weak classifiers efficiently according to the object being trackedt. It is a promising technique for o...
Developments in basic neurological research and techniques used to train professional athletes suggest that one way of facilitating this learning process of motor schemas is throug...
We present a new method for regularized convex optimization and analyze it under both online and stochastic optimization settings. In addition to unifying previously known firstor...
John Duchi, Shai Shalev-Shwartz, Yoram Singer, Amb...
My research attempts to address on-line action selection in reinforcement learning from a Bayesian perspective. The idea is to develop more effective action selection techniques b...