Distributed accelerated gradient methods with restart under quadratic growth condition
From MaRDI portal
Publication:6607027
Recommendations
- An accelerated distributed gradient method with local memory
- Distributed stochastic gradient tracking methods with momentum acceleration for non-convex optimization
- Communication-efficient distributed optimization of self-concordant empirical loss
- Distributed adaptive Newton methods with global superlinear convergence
- Distributed stochastic variance reduced gradient methods by sampling extra data with replacement
Cites work
- A Decentralized Primal-Dual Method for Constrained Minimization of a Strongly Convex Function
- A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems
- A Proximal Gradient Algorithm for Decentralized Composite Optimization
- Convergence Rates of Distributed Nesterov-Like Gradient Methods on Random Networks
- Convergence speed in distributed consensus and averaging
- Decentralized Accelerated Gradient Methods With Increasing Penalty Parameters
- Decentralized estimation of Laplacian eigenvalues in multi-agent systems
- Distributed Linearized Alternating Direction Method of Multipliers for Composite Convex Consensus Optimization
- Distributed optimization and statistical learning via the alternating direction method of multipliers
- Distributed Subgradient Methods for Multi-Agent Optimization
- EXTRA: an exact first-order algorithm for decentralized consensus optimization
- Fast convergence of inertial dynamics and algorithms with asymptotic vanishing viscosity
- Fast Distributed Gradient Methods
- Fast projection onto the simplex and the l₁ ball
- First-order methods in optimization
- From error bounds to the complexity of first-order descent methods for convex functions
- Global error bounds for piecewise convex polynomials
- scientific article; zbMATH DE number 3850830 (Why is no real title available?)
- Linear convergence of first order methods for non-strongly convex optimization
- Numerical Optimization
- Optimal convergence rates for convex distributed optimization in networks
- Robust Stopping Criteria for Dykstra's Algorithm
- RSG: Beating Subgradient Method without Smoothness and Strong Convexity
- The rate of convergence of Nesterov's accelerated forward-backward method is actually faster than 1/k^2
This page was built for publication: Distributed accelerated gradient methods with restart under quadratic growth condition
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6607027)
