A unified framework for decentralized stochastic subgradient methods with compressed communication is proposed, proving global convergence for nonsmooth nonconvex objectives via differential inclusions and developing new variants with numerical support.
Decentralized deep learning with arbitrary communication compression.arXiv preprint arXiv:1907.09356, 2019
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
math.OC 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
q-PDGD achieves linear convergence to a neighborhood under RSI with constant step-size and O(1/k) with diminishing steps in stochastic quantized distributed optimization, matching centralized rates.
citing papers explorer
-
Decentralized Stochastic Subgradient-type Methods with Communication Compression for Nonsmooth Nonconvex Optimization
A unified framework for decentralized stochastic subgradient methods with compressed communication is proposed, proving global convergence for nonsmooth nonconvex objectives via differential inclusions and developing new variants with numerical support.
-
Quantized Stochastic Primal-Dual Methods for Distributed Optimization under Relaxed Global Geometry
q-PDGD achieves linear convergence to a neighborhood under RSI with constant step-size and O(1/k) with diminishing steps in stochastic quantized distributed optimization, matching centralized rates.