11:00 AM in Everest
Martin Jaggi, post-doctoral researcher, Ecole Polytechnique, Palaiseau, France, give a talk based on joint work with Simon Lacoste-Julien, Mark Schmidt and Patrick Pletscher: Coordinate descent on one hand, and the Frank-Wolfe algorithm on the other hand are two of the earliest known first-order methods for convex optimization. Here we will combine the two methods to obtain a new randomized block-coordinate optimization algorithm for block-separable constrained problems, which appear for example in machine learning and computer vision. Learn more

Access instructions