mlsanityData to 14 Oct 2026

An Asynchronous Parallel Stochastic Coordinate Descent Algorithm

arXiv 1311.1873 ↗First posted 8 Nov 2013math.OCcited by 26

Not on the map. Why?

Abstract (arXiv)

We describe an asynchronous parallel stochastic coordinate descent algorithm for minimizing smooth unconstrained or separably constrained functions. The method achieves a linear convergence rate on functions that satisfy an essential strong convexity property and a sublinear rate (1/K) on general convex functions. Near-linear speedup on a multicore system can be expected if the number of processors is O(n1/2) in unconstrained optimization and O(n1/4) in the separable-constrained case, where n is the number of variables. We describe results from implementation on 40-core processors.

Key facts. Cited by 26 papers in the map (data through 14 Oct 2026). First posted on arXiv 8 Nov 2013.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 8; 2022: 10; 2023: 3; 2024: 4; 2025: 0; 2026: 1.

26 papers.

Sort:

  1. 2021Online Learning with Optimism and Delaycited by 33
  2. 2022Convergence of gradient descent for deep neural networkscited by 24
  3. 2021Proxy Convexity: A Unified Framework for the Analysis of Neural Networks Trained by Gradient Descentcited by 21
  4. 2022Stochastic Second-Order Methods Improve Best-Known Sample Complexity of SGD for Gradient-Dominated Functioncited by 20
  5. 2021Distributed Learning Systems with First-order Methodscited by 17
  6. 2021Asynchronous Iterations in Optimization: New Sequence Results and Sharper Algorithmic Guaranteescited by 17
  7. 2021Doubly Optimal No-Regret Online Learning in Strongly Monotone Games with Bandit Feedbackcited by 15
  8. 2022Efficient and Light-Weight Federated Learning via Asynchronous Distributed Dropoutcited by 12
  9. 2022Delay-adaptive step-sizes for asynchronous learningcited by 11
  10. 2024Loss Landscape Characterization of Neural Networks without Over-Parametrizationcited by 8
  11. 2022On generalization bounds for deep networks based on loss surface implicit regularizationcited by 5
  12. 2022Optimizing the Performative Risk under Weak Convexity Assumptionscited by 5
14 more
  1. 2022Asynchronous Gradient Play in Zero-Sum Multi-agent Gamescited by 5
  2. 2021Cyclic Coordinate Dual Averaging with Extrapolationcited by 3
  3. 2022A dual approach for federated learningcited by 3
  4. 2023Accelerated Cyclic Coordinate Dual Averaging with Extrapolation for Composite Convex Optimizationcited by 3
  5. 2024Second-order Information Promotes Mini-Batch Robustness in Variance-Reduced Gradientscited by 3
  6. 2021Coordinate Descent Methods for DC Minimization: Optimality Conditions and Global Convergencecited by 2
  7. 2022Adaptive Stochastic Gradient Descent for Fast and Communication-Efficient Distributed Learningcited by 2
  8. 2024Convex and Bilevel Optimization for Neuro-Symbolic Inference and Learningcited by 1
  9. 2021Learning Linear Models Using Distributed Iterative Hessian Sketchingcited by 0
  10. 2022A Machine Learning Framework for Distributed Functional Compression over Wireless Channels in IoTcited by 0
  11. 2023FedDec: Peer-to-peer Aided Federated Learningcited by 0
  12. 2023Distributed Dual Coordinate Ascent with Imbalanced Data on a General Tree Networkcited by 0
  13. 2024Accelerated Markov Chain Monte Carlo Using Adaptive Weighting Schemecited by 0
  14. 2026Continuous Optimization for p-adic Modelscited by 0