The kernel Perceptron is an appealing online learning algorithm that has a drawback: whenever it makes an error it must increase its support set, which slows training and testing ...
Conditional log-linear models are a commonly used method for structured prediction. Efficient learning of parameters in these models is therefore an important problem. This paper ...
Amir Globerson, Terry Koo, Xavier Carreras, Michae...
Maximum Margin Matrix Factorization (MMMF) was recently suggested (Srebro et al., 2005) as a convex, infinite dimensional alternative to low-rank approximations and standard facto...
We present metric?? , a provably near-optimal algorithm for reinforcement learning in Markov decision processes in which there is a natural metric on the state space that allows t...
The multi-armed bandit problem for a gambler is to decide which arm of a K-slot machine to pull to maximize his total reward in a series of trials. Many real-world learning and opt...