Towards accelerated rates for distributed optimization over time-varying networks

DOI10.1007/978-3-030-91059-4_19zbMath1527.90162arXiv2009.11069OpenAlexW3211480018MaRDI QIDQ6349702

A. V. Gasnikov, Dmitry P. Kovalev, zbMATH Open Web Interface contents unavailable due to conflicting licenses., Egor Shulgin, Alexander Rogozin

Publication date: 23 September 2020

Full work available at URL: https://doi.org/10.1007/978-3-030-91059-4_19

Mathematics Subject Classification ID

Convex programming (90C25) Communication networks in operations research (90B18)

Related Items

Min-max optimization over slowly time-varying graphs, Decentralized saddle-point problems with different constants of strong convexity and strong concavity, Decentralized optimization over slowly time-varying graphs: algorithms and lower bounds, Decentralized optimization with affine constraints over time-varying networks, Recent theoretical advances in decentralized distributed convex optimization

Cites Work

• First-order methods of smooth convex optimization with inexact oracle
• Accelerated and unaccelerated stochastic gradient descent in model generality
• Fast Distributed Gradient Methods
• Revisiting EXTRA for Smooth Distributed Optimization
• Fast Convergence Rates for Distributed Non-Bayesian Learning
• Achieving Geometric Convergence for Distributed Optimization Over Time-Varying Graphs
• Distributed Subgradient Methods for Multi-Agent Optimization
• Decentralized Accelerated Gradient Methods With Increasing Penalty Parameters
• EXTRA: An Exact First-Order Algorithm for Decentralized Consensus Optimization