2 citations · 2 across the 2 of their papers we have counts for
3 papers
math.OC2012
An acceleration procedure for optimal first-order methods
Michel Baes, Michael Buergisser
We introduce in this paper an optimal first-order method that allows an easy and cheap evaluation of the local Lipschitz constant of the objective's gradient. This constant must id…
math.OC2011
Hedge algorithm and Dual Averaging schemes
Michel Baes, Michael Bürgisser
We show that the Hedge algorithm, a method that is widely used in Machine Learning, can be interpreted as a particular instance of Dual Averaging schemes, which have recently been…
math.OC2011★ 2 cited
A randomized Mirror-Prox method for solving structured large-scale matrix saddle-point problems
Michel Baes, Michael Bürgisser, Arkadi Nemirovski
In this paper, we derive a randomized version of the Mirror-Prox method for solving some structured matrix saddle-point problems, such as the maximal eigenvalue minimization proble…