Min–max problems have broad applications in machine learning, including learning with
non-decomposable loss and learning with robustness to data distribution. Convex–concave …

We present a randomized primal-dual algorithm that solves the problem minx maxy y^ TA x
to additive error epsilon in time nnz (A)+ sqrt {nnz (A) n}/epsilon, for matrix A with larger …

We study the problem of minimizing a relatively-smooth convex function using stochastic
Bregman gradient methods. We first prove the convergence of Bregman Stochastic Gradient …

Distributionally robust supervised learning (DRSL) is emerging as a key paradigm for
building reliable machine learning systems for real-world applications–reflecting the need …

We investigate sublinear classical and quantum algorithms for matrix games, a fundamental
problem in optimization and machine learning, with provable guarantees. Given a matrix …

We consider the constrained optimization where the objective function and the constraints
are defined as summation of finitely many loss functions. This model has applications in …

This paper revisits the generic structured primal-dual problem involving the infimal
convolution in real Hilbert spaces. For this purpose, we develop a stochastic primal-dual …

In the study of stochastic mixed variational inequalities (SMVIs), Lipschitz is an
indispensable assumption for the convergence analysis. However, practical applications …

We propose a method that enables practitioners to conveniently incorporate custom non-
decomposable performance metrics into differentiable learning pipelines, notably those …

En apprentissage statistique et traitement du signal, de nombreuses tâches se formulent
sous la forme d'un problème d'optimisation de grande taille. Dans ce contexte, les méthodes …