Research map / Optimization / Distributed and compressed
Fast ADMM Algorithm for Distributed Optimization with Adaptive Penalty
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 ADMM-VP or ADMM-VP+AP penalty updates instead of fixed penalty | D-PPCA with ADMM · Hopkins 155 (complete network) | speed up in iterations: 40.2%, 37.3% speed up | Helped |
| Use ADMM-AP, ADMM-NAP or ADMM-VP+NAP instead of fixed penalty | D-PPCA with ADMM · Hopkins 155 | iterations to convergence | No clear effect |
| Use ring instead of complete network for ADMM-VP (ablation) | ADMM-VP · Hopkins 155 | speed up | Hurt |
| Increase number of nodes (12 to 20, complete graph) (ablation) | Proposed ADMM variants (esp. ADMM-VP) · Synthetic PPCA | speed up vs ADMM | Helped |
| Use ADMM-AP/NAP instead of ADMM-VP in weakly connected networks (ablation) | Penalty update · Synthetic PPCA, ring/cluster graphs | convergence speed | Helped |
| Reduce t_max from 50 to 5 for t_max-dependent methods (VP, AP, VP+AP) (ablation) | ADMM-VP/AP · Caltech Turntable SfM | acceleration | Hurt |
| Use ADMM-NAP with adaptive budget instead of fixed t_max (ablation) | ADMM penalty update · Caltech Turntable SfM, t_max=5 | acceleration | Helped |
| Replace tau_ij in ADMM-VP with the edge-wise adaptive tau (ablation) | ADMM-VP · preliminary experiments | convergence | No clear effect |
Closest papers by meaning
- Adaptive Consensus ADMM for Distributed Optimization (ICML 2017 · similarity 0.93)
- A Communication Efficient Stochastic Multi-Block Alternating Direction Method of Multipliers (NeurIPS 2019 · similarity 0.92)
- ADMM without a Fixed Penalty Parameter: Faster Convergence with New Adaptive Penalization (NeurIPS 2017 · similarity 0.92)
- An Accelerated Decentralized Stochastic Proximal Algorithm for Finite Sums (NeurIPS 2019 · similarity 0.88)
- Hybrid Decentralized Optimization: Leveraging Both First- and Zeroth-Order Optimizers for Faster Convergence (AAAI 2025 · similarity 0.87)
- ADMM for Nonconvex Optimization under Minimal Continuity Assumption (ICLR 2025 · similarity 0.87)
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.