Research map / Optimization / Nonconvex and smooth optimization
Prox-PDA: The Proximal Primal-Dual Algorithm for Fast Distributed Nonconvex Optimization and Learning Over Networks
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 proximal primal-dual (Prox-GPDA) with constant penalty instead of DSG/Push-sum baselines | distributed nonconvex binary classification · N=10 to N=50 nodes, 100k points | optimality gap (Table 1): 5.1e-36 vs 1.34 (DSG) and 2.79 (Push-sum) at N=10 | Helped |
| Use increasing penalty (Prox-GPDA-IP) instead of constant penalty (ablation) | Prox-GPDA · distributed binary classification, N=10 to 50 | optimality gap: 2.4e-22 vs 5.1e-36 at N=10; 4.2e-6 vs 5.5e-10 at N=50 | Hurt |
| Prox-PDA-IP (increasing penalty) vs EXTRA-AO on distributed matrix factorization | Prox-PDA-IP · distributed matrix factorization, N=10 on barbara patches | objective/optimality gap convergence speed | Helped |
| Push-sum baseline does not converge within 1000 iterations | push-sum baseline · distributed binary classification | consensus error / optimality gap | No clear effect |
Closest papers by meaning
- Gradient Primal-Dual Algorithm Converges to Second-Order Stationary Solution for Nonconvex Distributed Optimization Over Networks (ICML 2018 · similarity 0.92)
- A Simple Proximal Stochastic Gradient Method for Nonsmooth Nonconvex Optimization (NeurIPS 2018 · similarity 0.90)
- DASHA: Distributed Nonconvex Optimization with Communication Compression and Optimal Oracle Complexity (ICLR 2023 · similarity 0.89)
- An Online Optimization Perspective on First-Order and Zero-Order Decentralized Nonsmooth Nonconvex Stochastic Optimization (ICML 2024 · similarity 0.88)
- Stabilized Proximal-Point Methods for Federated Optimization (NeurIPS 2024 · similarity 0.88)
- Stochastic Smoothed Primal-Dual Algorithms for Nonconvex Optimization with Linear Inequality Constraints (ICML 2025 · 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.