Research map / Optimization / Nonconvex and smooth optimization
Trajectory of Alternating Direction Method of Multipliers and Adaptive Acceleration
Clarice Poon, Jingwei Liang
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 |
|---|---|---|---|
| Add inertial extrapolation to ADMM when z_k trajectory is a spiral (gamma = ||K||^2/10) | ADMM · LASSO, random Gaussian K (640x2048) | convergence speed | Mixed |
| Add inertial extrapolation to ADMM when z_k trajectory is a straight line (gamma = ||K||^2 + 0.1) | ADMM · LASSO, random Gaussian K (640x2048) | convergence speed | Improved |
| Add inertial ADMM on affine-constrained problems (l1, l1,2, nuclear norm) | ADMM · Affine constrained minimisation | convergence speed | No clear effect |
| Replace ADMM with A3DMM (adaptive trajectory-following extrapolation) | ADMM · Affine constrained minimisation | convergence speed | Improved |
| Replace ADMM with A3DMM | ADMM · LASSO on covtype, ijcnn1, phishing | convergence speed | Improved |
| Use s = +infinity instead of s = 100 in A3DMM (ablation) | A3DMM · Affine constrained minimisation | convergence speed | No clear effect |
| Use s = +infinity instead of s = 100 in A3DMM (ablation) | A3DMM · LASSO on LIBSVM datasets | convergence speed | Improved |
| Add inertial ADMM on LASSO LIBSVM datasets | ADMM · LASSO on covtype, ijcnn1, phishing | convergence speed | Improved |
Closest papers by meaning
- ADMM without a Fixed Penalty Parameter: Faster Convergence with New Adaptive Penalization (NeurIPS 2017 · similarity 0.89)
- ADMM and Accelerated ADMM as Continuous Dynamical Systems (ICML 2018 · similarity 0.88)
- Fast Proximal Linearized Alternating Direction Method of Multiplier with Parallel Splitting (AAAI 2016 · similarity 0.87)
- Optimizing ADMM and Over-Relaxed ADMM Parameters for Linear Quadratic Problems (AAAI 2024 · similarity 0.84)
- ADMM for Nonconvex Optimization under Minimal Continuity Assumption (ICLR 2025 · similarity 0.83)
- Adaptive Riemannian ADMM for Nonsmooth Optimization: Optimal Complexity without Smoothing (NeurIPS 2025 · similarity 0.83)
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.
