Research map / Optimization / Nonconvex and smooth optimization
CoCoA: A General Framework for Communication-Efficient Distributed Optimization
Virginia Smith, Simone Forte, Chenxin Ma, Martin Takáč, Michael I. Jordan, Martin Jaggi
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| run CoCoA in the primal instead of OWL-QN on lasso | lasso regression on distributed datasets · webspam | convergence speed: OWL-QN converges 50× more slowly | Improved |
| increase smoothing strength delta added to the L1 objective for CoCoA in the dual (ablation) | CoCoA-Dual on pure L1 regularization · lasso final iterate sparsity | sparsity of final iterates: 0.6035 -> 0.6240 -> 0.6465 as delta goes 0.0001 -> 0.001 -> 0.01 | Hurt |
| use CoCoA in the primal rather than smoothing and running in the dual (ablation) | CoCoA on non-strongly-convex regularizers · lasso | solution quality and convergence | Improved |
Closest papers by meaning
- Gradient Sparsification for Communication-Efficient Distributed Optimization (NeurIPS 2018 · similarity 0.89)
- A General Distributed Dual Coordinate Optimization Framework for Regularized Loss Minimization (JMLR 2017 · similarity 0.89)
- Efficient Distributed Learning with Sparsity (ICML 2017 · similarity 0.89)
- Communication-Efficient Gradient Descent-Accent Methods for Distributed Variational Inequalities: Unified Analysis and Local Updates (ICLR 2024 · similarity 0.88)
- Accelerated Methods with Compressed Communications for Distributed Optimization Problems Under Data Similarity (AAAI 2025 · similarity 0.88)
- Implicit Regularization of Decentralized Gradient Descent for Sparse Regression (NeurIPS 2024 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
