EF21-P and Friends: Improved Theoretical Communication Complexity for Distributed Optimization with Bidirectional Compression

Add to your list(s) Download to your calendar using vCal

• Kaja Gruntkowska (University of Oxford)
• Tuesday 07 March 2023, 14:00-15:00
• Law Building, 111; Zoom: https://bham-ac-uk.zoom.us/j/83945168193?pwd=UGQrU0EyNm5pUjNjNFhBNWlIbWlyQT09.

If you have a question about this talk, please contact Sergey Sergeev.

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. Our bounds are the first that manage to decouple the variance/error coming from the workers-to-server and server-to-workers compression, transforming a multiplicative dependence to an additive one. Moreover, in the convex regime, we obtain the first bounds that match the theoretical communication complexity of gradient descent. Even in this convex regime, our algorithms work with biased gradient estimators, which is non-standard and requires new proof techniques that may be of independent interest. Finally, our theoretical results are corroborated through suitable experiments.

This talk is part of the Optimisation and Numerical Analysis Seminars series.

This talk is included in these lists:

• Law Building, 111; Zoom: https://bham-ac-uk.zoom.us/j/83945168193?pwd=UGQrU0EyNm5pUjNjNFhBNWlIbWlyQT09
• Optimisation and Numerical Analysis Seminars
• School of Mathematics Events

Note that ex-directory lists are not shown.