In this paper, we propose a second order optimization method to learn models where both the dimensionality of the parameter space and the number of training samples is high. In ou...
Dynamic programming provides a methodology to develop planners and controllers for nonlinear systems. However, general dynamic programming is computationally intractable. We have ...
In this paper, we study an adaptive random search method based on continuous action-set learning automaton for solving stochastic optimization problems in which only the noisecorr...
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 prove logarithmic regret bounds that depend on the loss L∗ T of the competitor rather than on the number T of time steps. In the general online convex optimization setting, o...