Research map / Optimization / Distributed and compressed
A General Distributed Dual Coordinate Optimization Framework for Regularized Loss Minimization
Shun Zheng, Jialei Wang, Fen Xia, Wei Xu, Tong Zhang
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 |
|---|---|---|---|
| use accelerated Acc-DADM instead of CoCoA+ | distributed SDCA with ProxSDCA local solver · covtype, rcv1, HIGGS, kdd2010 (L2-L1 SVM and LR) | normalized duality gap | Improved |
| set momentum nu=0 instead of theory-suggested nu (ablation) | Acc-DADM · L2-L1 regularized loss minimization | convergence smoothness | No clear effect |
| increase local mini-batch sampling percentage sp (0.05, 0.20, 0.80) (ablation) | Acc-DADM and CoCoA+ · SVM and LR on four datasets | communications over 100 passes | Improved |
| use Acc-DADM instead of CoCoA+ when scaling machines | distributed dual coordinate ascent · scalability, lambda=1e-7 | communications or time to reach 1e-3 duality gap | Improved |
| apply acceleration without smoothing to non-smooth hinge loss | Acc-DADM · hinge loss SVM | normalized duality gap | Improved |
| use CoCoA+ with large regularization lambda | CoCoA+ · large lambda | normalized duality gap | No clear effect |
Closest papers by meaning
- Distributed Coordinate Descent Method for Learning with Big Data (JMLR 2016 · similarity 0.89)
- DSCOVR: Randomized Primal-Dual Block Coordinate Algorithms for Asynchronous Distributed Optimization (JMLR 2019 · similarity 0.89)
- Towards Stability and Generalization Bounds in Decentralized Minibatch Stochastic Gradient Descent (AAAI 2024 · similarity 0.87)
- Hybrid Decentralized Optimization: Leveraging Both First- and Zeroth-Order Optimizers for Faster Convergence (AAAI 2025 · similarity 0.86)
- Rescaled Asynchronous SGD: Optimal Distributed Optimization under Data and System Heterogeneity (NeurIPS 2026 · similarity 0.86)
- Accelerated Methods with Compressed Communications for Distributed Optimization Problems Under Data Similarity (AAAI 2025 · similarity 0.86)
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.
