As mobile phone becomes popular in the society and many people can afford the cost, the demand of mobility is extended to teaching and learning purposes. One recent and significan...
In this work, we extend the ellipsoid method, which was originally designed for convex optimization, for online learning. The key idea is to approximate by an ellipsoid the classi...
Applications of learning to autonomous agents (simulated or real) have often been restricted to learning a mapping from perceived state of the world to the next action to take. Of...
We describe a novel framework for the design and analysis of online learning algorithms based on the notion of duality in constrained optimization. We cast a sub-family of universa...
One of the key issues in designing appropriate and effective learning environments is understanding how learners advance and what factors contribute to their progress. This holds...