Communication-efficient algorithms for decentralized and stochastic optimization
From MaRDI portal
Publication:2297648
DOI10.1007/s10107-018-1355-4zbMath1437.90125arXiv1701.03961OpenAlexW2963855576WikidataQ128829704 ScholiaQ128829704MaRDI QIDQ2297648
Publication date: 20 February 2020
Published in: Mathematical Programming. Series A. Series B (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1701.03961
complexitystochastic programmingprimal-dual methoddecentralized optimizationnonsmooth functionscommunication efficientdecentralized machine learning
Convex programming (90C25) Stochastic programming (90C15) Numerical methods based on nonlinear programming (49M37) Decentralized systems (93A14)
Related Items (20)
Reducing the Complexity of Two Classes of Optimization Problems by Inexact Accelerated Proximal Gradient Method ⋮ Optimal Algorithms for Non-Smooth Distributed Optimization in Networks ⋮ Robust Asynchronous Stochastic Gradient-Push: Asymptotically Optimal and Network-Independent Performance for Strongly Convex Functions ⋮ Decentralized multi-agent optimization based on a penalty method ⋮ Exact penalties for decomposable convex optimization problems ⋮ Distributed communication-sliding mirror-descent algorithm for nonsmooth resource allocation problem ⋮ Distributed Sparse Composite Quantile Regression in Ultrahigh Dimensions ⋮ Graph Topology Invariant Gradient and Sampling Complexity for Decentralized and Stochastic Optimization ⋮ Communication-efficient and privacy-preserving large-scale federated learning counteracting heterogeneity ⋮ Distributed Decoding From Heterogeneous 1-Bit Compressive Measurements ⋮ Stochastic first-order methods for convex and nonconvex functional constrained optimization ⋮ Recent theoretical advances in decentralized distributed convex optimization ⋮ Revisiting EXTRA for Smooth Distributed Optimization ⋮ Distributed stochastic gradient tracking methods ⋮ Decentralized and parallel primal and dual accelerated methods for stochastic convex programming problems ⋮ Incremental without replacement sampling in nonconvex optimization ⋮ A randomized incremental primal-dual method for decentralized consensus optimization ⋮ Unnamed Item ⋮ A dual approach for optimal algorithms in distributed optimization over networks ⋮ Fast Decentralized Nonconvex Finite-Sum Optimization with Recursive Variance Reduction
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Distributed Optimization and Statistical Learning via the Alternating Direction Method of Multipliers
- Gradient sliding for composite optimization
- On the ergodic convergence rates of a first-order primal-dual algorithm
- An optimal method for stochastic composite optimization
- Distributed stochastic subgradient projection algorithms for convex optimization
- Incremental proximal methods for large scale convex optimization
- Validation analysis of mirror descent stochastic approximation method
- An optimal randomized incremental gradient method
- A first-order primal-dual algorithm for convex problems with applications to imaging
- On the $O(1/n)$ Convergence Rate of the Douglas–Rachford Alternating Direction Method
- Distributed Optimization Over Time-Varying Directed Graphs
- Fast Distributed Gradient Methods
- On the Complexity of the Hybrid Proximal Extragradient Method for the Iterates and the Ergodic Mean
- Complexity of Variants of Tseng's Modified F-B Splitting and Korpelevich's Methods for Hemivariational Inequalities with Applications to Saddle-point and Convex Optimization Problems
- Incremental Stochastic Subgradient Algorithms for Convex Optimization
- Robust Stochastic Approximation Approach to Stochastic Programming
- Distributed asynchronous deterministic and stochastic gradient optimization algorithms
- Convergence Rate of Distributed ADMM Over Networks
- Distributed Linearized Alternating Direction Method of Multipliers for Composite Convex Consensus Optimization
- On the Linear Convergence of the ADMM in Decentralized Consensus Optimization
- Multi-Agent Distributed Optimization via Inexact Consensus ADMM
- A Proximal Gradient Algorithm for Decentralized Composite Optimization
- Achieving Geometric Convergence for Distributed Optimization Over Time-Varying Graphs
- Stochastic Proximal Gradient Consensus Over Random Networks
- DQM: Decentralized Quadratically Approximated Alternating Direction Method of Multipliers
- Harnessing Smoothness to Accelerate Distributed Optimization
- Prox-Method with Rate of Convergence O(1/t) for Variational Inequalities with Lipschitz Continuous Monotone Operators and Smooth Convex-Concave Saddle Point Problems
- Optimal Stochastic Approximation Algorithms for Strongly Convex Stochastic Composite Optimization I: A Generic Algorithmic Framework
- Distributed Subgradient Methods for Multi-Agent Optimization
- Optimal Primal-Dual Methods for a Class of Saddle Point Problems
- An Accelerated Linearized Alternating Direction Method of Multipliers
- EXTRA: An Exact First-Order Algorithm for Decentralized Consensus Optimization
- On the Convergence Rate of Incremental Aggregated Gradient Algorithms
- Coordination of groups of mobile autonomous agents using nearest neighbor rules
- Iteration-Complexity of Block-Decomposition Algorithms and the Alternating Direction Method of Multipliers
- Asynchronous Broadcast-Based Convex Optimization Over a Network
- On Distributed Convex Optimization Under Inequality and Equality Constraints
- Dual Averaging for Distributed Optimization: Convergence Analysis and Network Scaling
- Optimal Stochastic Approximation Algorithms for Strongly Convex Stochastic Composite Optimization, II: Shrinking Procedures and Optimal Algorithms
This page was built for publication: Communication-efficient algorithms for decentralized and stochastic optimization
