Abstract. The presence of long gaps dramatically increases the difficulty of detecting and characterizing complex events hidden in long sequences. In order to cope with this proble...
We consider the task of reinforcement learning with linear value function approximation. Temporal difference algorithms, and in particular the Least-Squares Temporal Difference (L...
We consider the minimization of a smooth loss with trace-norm regularization, which is a natural objective in multi-class and multitask learning. Even though the problem is convex...
We propose a semi-supervised learning algorithm for discriminant analysis, which uses the geometric structure of both labeled and unlabeled samples and perform a manifold regulari...
Matrix factorization into the product of lowrank matrices induces non-identifiability, i.e., the mapping between the target matrix and factorized matrices is not one-to-one. In th...