Research map / Optimization / Optimizers
Adaptive Relaxed ADMM: Convergence Theory and Practical Implementation
Check 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 |
|---|---|---|---|
| jointly adapt the penalty and relaxation parameters instead of using Adaptive ADMM | ARADMM · Elastic net regression, Synthetic | iterations to convergence: 102 -> 70 | Helped |
| jointly adapt the penalty and relaxation parameters instead of using Adaptive ADMM | ARADMM · Elastic net regression, MNIST | iterations to convergence: 41 -> 21 | Helped |
| jointly adapt the penalty and relaxation parameters instead of using Adaptive ADMM | ARADMM · Low-rank least squares, Synthetic | iterations to convergence: 26 -> 18 | Helped |
| jointly adapt the penalty and relaxation parameters instead of using Adaptive ADMM | ARADMM · Low-rank least squares, CIFAR10 | iterations to convergence: 8 -> 6 | Helped |
| jointly adapt the penalty and relaxation parameters instead of using Adaptive ADMM | ARADMM · QP and dual SVM, Synthetic | iterations to convergence: 170 -> 100 | Helped |
| jointly adapt the penalty and relaxation parameters instead of using Adaptive ADMM | ARADMM · Consensus logistic regression, Synthetic | iterations to convergence: 35 -> 20 | Helped |
| jointly adapt the penalty and relaxation parameters instead of using Relaxed ADMM | ARADMM · Unwrapped SVM, German | iterations to convergence: 560 -> 213 | Helped |
| jointly adapt the penalty and relaxation parameters instead of using Relaxed ADMM | ARADMM · Unwrapped SVM, MNIST | iterations to convergence: 118 -> 67 | Helped |
| jointly adapt the penalty and relaxation parameters instead of using Adaptive ADMM | ARADMM · Image denoising, Barbara | iterations to convergence: 59 -> 38 | Helped |
| jointly adapt the penalty and relaxation parameters instead of using Residual balance | ARADMM · Robust PCA, FaceSet1 | iterations to convergence: 560 -> 267 | Helped |
| vary safeguarding correlation threshold (ablation) | ARADMM · multiple applications | iterations to convergence | No clear effect |
Closest papers by meaning
- ADMM without a Fixed Penalty Parameter: Faster Convergence with New Adaptive Penalization (NeurIPS 2017 · similarity 0.91)
- Optimizing ADMM and Over-Relaxed ADMM Parameters for Linear Quadratic Problems (AAAI 2024 · similarity 0.90)
- ADMM for Nonconvex Optimization under Minimal Continuity Assumption (ICLR 2025 · similarity 0.89)
- Adaptive Riemannian ADMM for Nonsmooth Optimization: Optimal Complexity without Smoothing (NeurIPS 2025 · similarity 0.86)
- ADMM for Structured Fractional Minimization (ICLR 2025 · similarity 0.86)
- Decoupling Training-Free Guided Diffusion by ADMM (CVPR 2025 · similarity 0.85)
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.