We present new theoretical convergence results on the Cross-Entropy method for discrete optimization. Our primary contribution is to show that a popular implementation of the Cros...
This paper introduces a novel energy minimization method, namely iterated cross entropy with partition strategy (ICEPS), into the Markov random field theory. The solver, which is...
We present a learning framework for Markovian decision processes that is based on optimization in the policy space. Instead of using relatively slow gradient-based optimization al...
We consider support vector machines for binary classification. As opposed to most approaches we use the number of support vectors (the "L0 norm") as a regularizing term ...