CommunicationAccelerationofLocalGradient MethodsviaanAcceleratedPrimal-DualAlgorithm withInexactProx

Feb-10-2026, 13:30:13 GMT–Neural Information Processing Systems

However, all known theoretical rates are worse than the rate of gradient descent, which synchronizes after every gradient step.

artificial intelligence, arxivpreprintarxiv, machine learning, (17 more...)

Neural Information Processing Systems

Feb-10-2026, 13:30:13 GMT

Conferences PDF

Country:
- Asia
  - Middle East > Jordan (0.04)
  - Russia (0.04)
- Europe > Russia
  - Central Federal District > Moscow Oblast > Moscow (0.04)
- North America > United States
  - California (0.04)

Technology:
- Information Technology > Artificial Intelligence
  - Machine Learning > Statistical Learning
    - Gradient Descent (0.48)
  - Representation & Reasoning (1.00)

Duplicate Docs Excel Report

Title
Communication Acceleration of Local Gradient Methods via an Accelerated Primal-Dual Algorithm with Inexact Prox

Similar Docs Excel Report more

Title	Similarity	Source
None found