DSA: Decentralized Double Stochastic Averaging Gradient Algorithm

zbMath1360.68699arXiv1506.04216MaRDI QIDQ2810864

Alejandro Ribeiro, Aryan Mokhtari

Publication date: 6 June 2016

Full work available at URL: https://arxiv.org/abs/1506.04216

zbMATH Keywords

stochastic optimizationlarge-scale optimizationlinear convergencelogistic regressiondecentralized optimizationstochastic averaging gradient

Mathematics Subject Classification ID

General nonlinear regression (62J02) Learning and adaptive systems in artificial intelligence (68T05) Stochastic programming (90C15)

Related Items (21)

Optimal Algorithms for Non-Smooth Distributed Optimization in Networks ⋮ Graph-Dependent Implicit Regularisation for Distributed Stochastic Subgradient Descent ⋮ Primal-dual algorithm for distributed constrained optimization ⋮ Differentially private distributed optimization for multi-agent systems via the augmented Lagrangian algorithm ⋮ Linear convergence of primal-dual gradient methods and their performance in distributed optimization ⋮ A stochastic averaging gradient algorithm with multi‐step communication for distributed optimization ⋮ Multi-cluster distributed optimization via random sleep strategy ⋮ Decentralized learning over a network with Nyström approximation using SGD ⋮ Achieving Geometric Convergence for Distributed Optimization Over Time-Varying Graphs ⋮ Revisiting EXTRA for Smooth Distributed Optimization ⋮ Decentralized Consensus Algorithm with Delayed and Stochastic Gradients ⋮ Surpassing Gradient Descent Provably: A Cyclic Incremental Method with Linear Convergence Rate ⋮ An Optimal Algorithm for Decentralized Finite-Sum Optimization ⋮ Augmented Lagrange algorithms for distributed optimization over multi-agent networks via edge-based method ⋮ Fully asynchronous policy evaluation in distributed reinforcement learning over networks ⋮ A randomized incremental primal-dual method for decentralized consensus optimization ⋮ Dualize, split, randomize: toward fast nonsmooth optimization algorithms ⋮ Unnamed Item ⋮ Primal-dual stochastic distributed algorithm for constrained convex optimization ⋮ On the convergence of exact distributed generalisation and acceleration algorithm for convex optimisation ⋮ Fast Decentralized Nonconvex Finite-Sum Optimization with Recursive Variance Reduction

This page was built for publication: DSA: Decentralized Double Stochastic Averaging Gradient Algorithm