We introduce and analyse a new family of algorithms which generalizes and unifies both the mirror descent and the dual averaging algorithms. In the framework of this family, we define a new algorithm for constrained optimization with the aim of combining the advantages of mirror descent and dual averaging. In practice, this new algorithm converges as fast as mirror descent and dual averaging, and in some situations greatly outperforms them. Besides, we demonstrate how our algorithms can also be applied to solving variational inequalities. 

This is joint work with Anatoli Juditsky and Eric Moulines.

The goal of this talk is to introduce the audience to the problem of algorithmic fairness. I will provide a general overview on the topic, describe various available notions of fairness in classification and regression, and present main approaches to tackle this problem. I will also present some recent theoretical results both in classification and regression.

This talk is based on joint works with C. Denis, M. Hebiri, L. Oneto, and M. Pontil.