Primal-dual stochastic subgradient methods for uniformly convex minimization

International audienceWe discuss non-Euclidean stochastic approximation algorithms for optimization problems with strongly and uniformly convex objectives. These algorithms are adaptive with respect to the parameters regularity and of strong or uniform convexity of the objective: in the case when the total number of iterations N is fixed, their accuracy coincides, up to a logarithmic in N factor with the accuracy of optimal algorithms