An Asynchronous Parallel Stochastic Coordinate Descent Algorithm

From MaRDI portal
Publication:5502117

zbMath1337.68286arXiv1311.1873MaRDI QIDQ5502117

Victor Bittorf, Stephen J. Wright, Srikrishna Sridhar, Christopher Re, Ji Liu

Publication date: 17 August 2015

Full work available at URL: https://arxiv.org/abs/1311.1873



Related Items

Accelerated, Parallel, and Proximal Coordinate Descent, An Accelerated Randomized Proximal Coordinate Gradient Method and its Application to Regularized Empirical Risk Minimization, A class of smooth exact penalty function methods for optimization problems with orthogonality constraints, Distributed Block Coordinate Descent for Minimizing Partially Separable Functions, An asynchronous inertial algorithm for solving convex feasibility problems with strict pseudo-contractions in Hilbert spaces, Unnamed Item, Unnamed Item, On unbounded delays in asynchronous parallel fixed-point algorithms, Linear convergence of first order methods for non-strongly convex optimization, Perturbed Iterate Analysis for Asynchronous Stochastic Optimization, A framework for parallel second order incremental optimization algorithms for solving partially separable problems, Cyclic Coordinate Dual Averaging with Extrapolation, Asynchronous Stochastic Coordinate Descent: Parallelism and Convergence Properties, Parallel and distributed asynchronous adaptive stochastic gradient methods, On the convergence of asynchronous parallel iteration with unbounded delays, Randomized Block Proximal Damped Newton Method for Composite Self-Concordant Minimization, A linearly convergent doubly stochastic Gauss-Seidel algorithm for solving linear equations and a certain class of over-parameterized optimization problems, On the rates of convergence of parallelized averaged stochastic gradient algorithms, On the Global Convergence of Randomized Coordinate Gradient Descent for Nonconvex Optimization, Convergence of the forward-backward algorithm: beyond the worst-case with the help of geometry, Convergence of an asynchronous block-coordinate forward-backward algorithm for convex composite optimization, Variance reduction for root-finding problems, Asynchronous parallel algorithms for nonconvex optimization, On the parallelization upper bound for asynchronous stochastic gradients descent in non-convex optimization, Stochastic block-coordinate gradient projection algorithms for submodular maximization, Worst-case complexity of cyclic coordinate descent: \(O(n^2)\) gap with randomized version, Asynchronous parallel primal-dual block coordinate update methods for affinely constrained convex programs, Parallel Stochastic Asynchronous Coordinate Descent: Tight Bounds on the Possible Parallelism, Fully asynchronous stochastic coordinate descent: a tight lower bound on the parallelism achieving linear speedup, A distributed quantile estimation algorithm of heavy-tailed distribution with massive datasets, Decentralized Consensus Algorithm with Delayed and Stochastic Gradients, Optimization Methods for Large-Scale Machine Learning, Asynchronous Lagrangian scenario decomposition, Two Symmetrized Coordinate Descent Methods Can Be $O(n^2)$ Times Slower Than the Randomized Version, Resolving learning rates adaptively by locating stochastic non-negative associated gradient projection points using line searches, Parallel decomposition methods for linearly constrained problems subject to simple bound with application to the SVMs training, Redundancy Techniques for Straggler Mitigation in Distributed Optimization and Learning, Distributed Learning with Sparse Communications by Identification, Improved asynchronous parallel optimization analysis for stochastic incremental methods, ARock: An Algorithmic Framework for Asynchronous Parallel Coordinate Updates, Parallelizable Algorithms for Optimization Problems with Orthogonality Constraints, CoordinateWise Descent Methods for Leading Eigenvalue Problem, Optimization in High Dimensions via Accelerated, Parallel, and Proximal Coordinate Descent, Accelerate stochastic subgradient method by leveraging local growth condition, Unnamed Item, A generic coordinate descent solver for non-smooth convex optimisation, Coordinate descent algorithms


Uses Software