Skip to main content
King Abdullah University of Science and Technology
Mechatronics and Energy Systems
Mechatronics and Energy Systems

Main navigation

  • Home
  • People
    • All Profiles
    • Principal Investigators
    • Research Scientists
    • Research Staff
    • Postdoctoral Fellows
    • Students
    • Alumni
    • Former Members
  • Events
    • All Events
    • Events Calendar
  • News
  • Contacts

gradient descent operation

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.

Mechatronics and Energy Systems (MERGE)

Footer

  • A-Z Directory
    • All Content
    • Browse Related Sites
  • Site Management
    • Log in

© 2025 King Abdullah University of Science and Technology. All rights reserved. Privacy Notice

Disclaimer: The views and opinions expressed in this page are strictly those of the page author. The contents of this page have not been reviewed or approved by the King Abdullah University of Science and Technology.