Research map / Optimization / Nonconvex and smooth optimization
A Single-Loop Gradient Descent and Perturbed Ascent Algorithm for Nonconvex Functional Constrained Optimization
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 |
|---|---|---|---|
| single-loop primal-dual GDPA with perturbed dual update instead of double/triple-loop inner solvers | nonconvex functional inequality constrained problems · theoretical convergence | iteration complexity to approximate KKT point | No clear effect |
| dual perturbation term (tau, gamma_r) in the dual update (ablation) | GDPA dual variable · theoretical analysis | dual variable bound / convergence | Helped |
| GDPA vs. IALM, IQRC, IPPP on MNIST multi-class Neyman-Pearson classification | GDPA · mNPC on MNIST | computing time convergence | Helped |
| GDPA vs. IQRC and IPPP on constraint satisfaction in mNPC | GDPA · mNPC on MNIST | feasibility convergence | Mixed |
| GDPA vs. baselines on neural net training with budget constraints | GDPA · MNIST fair training with accuracy budgets | computing time convergence | Helped |
Closest papers by meaning
- Universal Gradient Descent Ascent Method for Nonconvex-Nonconcave Minimax Optimization (NeurIPS 2023 · similarity 0.90)
- SLM: A Smoothed First-Order Lagrangian Method for Structured Constrained Nonconvex Optimization (NeurIPS 2023 · similarity 0.89)
- Near-Optimal Solutions of Constrained Learning Problems (ICLR 2024 · similarity 0.88)
- High-probability complexity bounds for stochastic non-convex minimax optimization (NeurIPS 2024 · similarity 0.87)
- Stochastic Smoothed Primal-Dual Algorithms for Nonconvex Optimization with Linear Inequality Constraints (ICML 2025 · similarity 0.87)
- Semi-infinite Nonconvex Constrained Min-Max Optimization (NeurIPS 2025 · similarity 0.86)
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.