2 papers
math.OC2026
Towards Noise-adaptive, Problem-adaptive (Accelerated) Stochastic Gradient Descent
Sharan Vaswani, Benjamin Dubois-Taine, Reza Babanezhad
We aim to make stochastic gradient descent (SGD) adaptive to (i) the noise in the stochastic gradients and (ii) problem-dependent constants. When minimizing smooth, strongly…
math.OC2026
Two-stage stochastic algorithm for solving large-scale (non)-convex separable optimization problems under affine constraints
Benjamin Dubois-Taine, Laurent Pfeiffer, Nadia Oudjane +2
We consider nonsmooth optimization problems under affine constraints, where the objective consists of the average of the component functions of a large number of agents, and we…