We develop and analyze MARINA: a new communication efficient method for non-convex
distributed learning over heterogeneous datasets. MARINA employs a novel communication …

We develop and analyze DASHA: a new family of methods for nonconvex distributed
optimization problems. When the local functions at the nodes have a finite-sum or an …

Matrix-stepsized gradient descent algorithms have been shown to have superior
performance in non-convex optimization problems compared to their scalar counterparts …

To find the optimal policy quickly for reinforcement learning problems, policy gradient (PG)
method is very effective, it parameters the policy and updates policy parameter directly …

This paper proposes a novel federated algorithm that leverages momentum-based variance
reduction with adaptive learning to address non-convex settings across heterogeneous …

In this thesis, we propose new theoretical frameworks for the analysis of stochastic and
distributed methods with error compensation and local updates. Using these frameworks, we …

Aquatic primary productivity mainly depends on pelagic phytoplankton. The globally
abundant marine picocyanobacteria Prochlorococcus comprises a significant fraction of the …