This work was done while M. Menart was at The Ohio State University.

This kernel is central to describe the generalization features ofANNs.

Regularized empirical risk minimization problem with linear predictor appears frequentlyinmachinelearning.

In terms of g(, y), we consider two settings - strongly convex and nonconvex - and improve upon the best known rates in both. For strongly-convex g(, y), y, we propose a new direct optimal algorithm combining Mirror-Prox and Nesterov's AGD, and show that it can find global optimum in Õ (1/k

This paper studies minimax optimization problemsminxmaxyf(x,y), where f(x,y) is mx-strongly convex with respect tox, my-strongly concave with respect to y and (Lx,Lxy,Ly)-smooth. Zhang et al. [42] provided the following lower bound of the gradient complexity for any first-order method: Ω q