gradient descent operation

Last-Iterate Convergence of Optimistic Multiplicative Weights Update

Francesco Orabona, Associate Professor, Computer Science

Oct 5, 12:00 - 13:00

B9 R2325

gradient descent operation optimistic gradient descent ascent convex optimization saddle-point problems

This talk will show how OMWU converges asymptotically for smooth convex-concave saddle-point problems, with a small enough constant learning rate.

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.