Alexander Tyurin

Asynchronous Policy Gradient Aggregation for Efficient Distributed Reinforcement Learning

Birch SGD: A Tree Graph Framework for Local and Asynchronous SGD Methods

Proving the Limited Scalability of Centralized Distributed Optimization via a New Lower Bound Construction

Bridging the Gap Between Homogeneous and Heterogeneous Asynchronous Optimization is Surprisingly Difficult

Local SGD and Federated Averaging Through the Lens of Time Complexity

Tighter Performance Theory of FedExProx

Learning of Population Dynamics: Inverse Optimization Meets JKO Scheme

Near-Optimal Convergence of Accelerated Gradient Methods under Generalized and $(L_0, L_1)$-Smoothness

Toward a Unified Theory of Gradient Descent under Generalized Smoothness

Tight Time Complexities in Parallel Stochastic Optimization with Arbitrary Computation Dynamics

Ringmaster ASGD: The First Asynchronous SGD with Optimal Time Complexity

Tighter Performance Theory of FedExProx