Research map / Optimization / Nonconvex and smooth optimization
A first-order primal-dual method with adaptivity to local smoothness
Maria-Luiza Vladarean, Yura Malitsky, Volkan Cevher
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 adaptive primal-dual stepsizes instead of CVA's fixed stepsizes | APDA versus CVA · Nonconvex phase retrieval reconstruction | PSNR: 20.56 -> 21.34 | Improved |
| Use adaptive primal-dual stepsizes instead of CVA's fixed stepsizes | APDA versus CVA · Nonconvex phase retrieval reconstruction | SSIM: 0.70 -> 0.76 | Improved |
| Use adaptive primal-dual stepsizes instead of CVA's fixed stepsizes | APDA versus CVA · Image inpainting reconstruction | PSNR: 25.63 -> 25.63 | No clear effect |
| Use adaptive primal-dual stepsizes instead of CVA's fixed stepsizes | APDA versus CVA · Image inpainting reconstruction | SSIM: 0.91 -> 0.91 | No clear effect |
| Use APDA rather than CVA | Sparse binary logistic regression · ijcnn, a9a, and mushrooms | convergence speed | Improved |
| Use APDA rather than CVA | Sparse binary logistic regression · covtype | convergence speed | Hurt |
| Use APDA rather than CVA | Adaptive primal-dual solver · Nonconvex phase retrieval | convergence across the stepsize grid: 32/40 grid points; all instances | Improved |
Closest papers by meaning
- On Linear Convergence in Smooth Convex-Concave Bilinearly-Coupled Saddle-Point Optimization: Lower Bounds and Optimal Algorithms (ICML 2025 · similarity 0.89)
- Faster Accelerated First-order Methods for Convex Optimization with Strongly Convex Function Constraints (NeurIPS 2024 · similarity 0.88)
- Efficiently Escaping Saddle Points under Generalized Smoothness via Self-Bounding Regularity (NeurIPS 2025 · similarity 0.87)
- Adaptive Proximal Gradient Method for Convex Optimization (NeurIPS 2024 · similarity 0.87)
- Second-Order Min-Max Optimization with Lazy Hessians (ICLR 2025 · similarity 0.87)
- Adaptive and Optimal Second-order Optimistic Methods for Minimax Optimization (NeurIPS 2024 · 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.
