Poster
Communication Complexity of Distributed Convex Learning and Optimization
Yossi Arjevani · Ohad Shamir

Mon Dec 7th 07:00 -- 11:59 PM @ 210 C #99 #None

We study the fundamental limits to communication-efficient distributed methods for convex learning and optimization, under different assumptions on the information available to individual machines, and the types of functions considered. We identify cases where existing algorithms are already worst-case optimal, as well as cases where room for further improvement is still possible. Among other things, our results indicate that without similarity between the local objective functions (due to statistical data similarity or otherwise) many communication rounds may be required, even if the machines have unbounded computational power.

Author Information

Yossi Arjevani (The Weizmann Institute)
Ohad Shamir (Weizmann Institute of Science)

More from the Same Authors