We consider sequential quadratic programming (SQP) methods for solving constrained nonlinear programming problems. It is generally believed that SQP methods are sensitive to the a...
We propose a novel approach to optimize Partially Observable Markov Decisions Processes (POMDPs) defined on continuous spaces. To date, most algorithms for model-based POMDPs are ...
Josep M. Porta, Nikos A. Vlassis, Matthijs T. J. S...
We propose a modified alternate direction method for solving convex quadratically constrained quadratic semidefinite optimization problems. The method is a first-order method, the...
Many practitioners who use EM and related algorithms complain that they are sometimes slow. When does this happen, and what can be done about it? In this paper, we study the gener...
Ruslan Salakhutdinov, Sam T. Roweis, Zoubin Ghahra...
It is known that the Karush-Kuhn-Tucker (KKT) conditions of semidefinite programming can be reformulated as a nonsmooth system via the metric projector over the cone of symmetric ...