distributed optimization

Theoretical Foundations of Communication-Efficient, Robust, and Practical Distributed and Federated Optimization

Grigory Malinovsky, Ph.D. Student, Applied Mathematics and Computational Science

Jun 18, 15:45 - 19:00

B5 R5209

machine learning Federated learning distributed optimization applied statistics

This thesis investigates seven critical challenges at the intersection of theory and practice, specifically focusing on the fundamental bottlenecks of Federated Learning and distributed optimization and develops novel algorithmic frameworks that provide sharp theoretical guarantees to bridge the gap between heuristic success and mathematical rigor.

EF21-P and friends: Improved theoretical communication complexity for distributed optimization with bidirectional compression

Feb 6, 12:00 - 13:00

B9 L2 H2 H2

EF21-P distributed optimization gradient descent operation

In this work we focus our attention on distributed optimization problems in the context where the communication time between the server and the workers is non-negligible. We obtain novel methods supporting bidirectional compression (both from the server to the workers and vice versa) that enjoy new state-of-the-art theoretical communication complexity for convex and nonconvex problems.

Grigory Malinovsky

Ph.D. Student, Applied Mathematics and Computational Science

machine learning optimization applied statistics stochastic optimization distributed optimization Federated learning