Fast Convergence Rates of Distributed Subgradient Methods With Adaptive Quantization

DOI10.1109/TAC.2020.3014095MaRDI QIDQ4990221zbMATH OpenFDO

Authors Thinh T. Doan, Siva Theja Maguluri, Justin Romberg

Publication date 28 May 2021

Published in IEEE Transactions on Automatic Control (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1810.13245

Mathematics Subject Classification ID

Systems theory; control (93-XX)

Cited in

(13)

• Convergence rate analysis of distributed optimization with projected subgradient algorithm
• A novel bound on the convergence rate of ADMM for distributed optimization
• Quantized Consensus by the ADMM: Probabilistic Versus Deterministic Quantizers
• Convergence Rates of Distributed Gradient Methods Under Random Quantization: A Stochastic Approximation Approach
• Linear Convergence of ADMM Under Metric Subregularity for Distributed Optimization
• Decentralized ADMM with compressed and event-triggered communication
• Decentralized online convex optimization with compressed communications
• Fast Convergence Rates of Distributed Subgradient Methods with Adaptive Quantization
• Distributed constrained optimization with periodic dynamic quantization
• Distributed constrained online convex optimization with adaptive quantization
• Numerical methods for distributed stochastic compositional optimization problems with aggregative structure
• Communication-efficient ADMM using quantization-aware Gaussian process regression
• On model-free learning over rate-limited channels: the linear quadratic regulator case

This page was built for publication: Fast Convergence Rates of Distributed Subgradient Methods With Adaptive Quantization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4990221)