Research map / Optimization / Nonconvex and smooth optimization
SLM: A Smoothed First-Order Lagrangian Method for Structured Constrained Nonconvex 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 |
|---|---|---|---|
| use SLM instead of V-PBGD | bilevel hyper-cleaning · MNIST hyper-cleaning | test accuracy after >3000 iterations: 88.1 -> 88.8 | Helped |
| use SLM instead of V-PBGD | bilevel hyper-cleaning · MNIST hyper-cleaning | constraint error: 0.68 -> 0.001 | Helped |
| use SLM instead of V-PBGD | bilevel hyper-cleaning · MNIST hyper-cleaning | peak test accuracy | No clear effect |
| use SLM (delta = 1) instead of V-PBGD | 2-layer NN · MNIST | peak test accuracy: 94.65 -> 94.74 | No clear effect |
| use SLM (delta = 1) instead of BOME | 2-layer NN · MNIST | peak test accuracy: 94.52 -> 94.74 | Helped |
| reduce constraint tolerance delta from 1 to 0.5 (ablation) | SLM · 2-layer NN on MNIST | convergence speed and peak accuracy: 94.74 -> 94.53 | Hurt |
| use SLM instead of BOME and V-PBGD | bilevel toy example · toy example | upper-level objective value | Helped |
| use SLM instead of BOME | 2-layer NN · MNIST | late-stage test accuracy | Helped |
Closest papers by meaning
- TSP: A Two-Sided Smoothed Primal-Dual Method for Nonconvex Bilevel Optimization (ICML 2025 · similarity 0.91)
- Optimal Hessian/Jacobian-Free Nonconvex-PL Bilevel Optimization (ICML 2024 · similarity 0.88)
- Constrained Bi-Level Optimization: Proximal Lagrangian Value Function Approach and Hessian-free Algorithm (ICLR 2024 · similarity 0.88)
- A Single-Loop First-Order Algorithm for Linearly Constrained Bilevel Optimization (NeurIPS 2025 · similarity 0.87)
- A Nearly Optimal Single Loop Algorithm for Stochastic Bilevel Optimization under Unbounded Smoothness (ICML 2024 · similarity 0.87)
- Generalized Smooth Bilevel Optimization with Nonconvex Lower-Level (ICML 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.