Research map / Optimization / Nonconvex and smooth optimization
A Multi-step Inertial Forward-Backward Splitting Method for Non-convex 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 |
|---|---|---|---|
| multi-step inertial steps (s=2, '2-iFB') instead of single-step inertia ('1-iFB') (ablation) | MiFB forward-backward for sparse regression, PCP, sparse SVM · synthetic sparse regression / PCP / sparse SVM (gamma=0.3/L) | ||x_k - x*|| convergence speed | Helped |
| inertial acceleration (MiFB with s=1 or s=2) instead of plain forward-backward (ablation) | forward-backward splitting · synthetic sparse regression / PCP / sparse SVM (gamma=0.3/L) | ||x_k - x*|| convergence speed and identification time | Helped |
| larger step size gamma=0.8/L with empirical inertial bound (2.4) instead of Theorem 2.2 choice of inertial parameters (ablation) | MiFB inertial parameter selection · synthetic sparse regression / PCP / sparse SVM | convergence speed of ||x_k - x*|| | Helped |
| choosing sum of inertial parameters close to 1 for gamma in (0, 2/(3L)] | MiFB · synthetic experiments | stability of iterates | Hurt |
| negative inertial parameters allowed (unlike prior work) | MiFB convergence theory · theoretical | convergence guarantee | No clear effect |
Closest papers by meaning
- Decentralized Gradient-Free Methods for Stochastic Non-smooth Non-convex Optimization (AAAI 2024 · similarity 0.87)
- Non-geodesically-convex optimization in the Wasserstein space (NeurIPS 2024 · similarity 0.87)
- Nonlinearly Preconditioned Gradient Methods under Generalized Smoothness (ICML 2025 · similarity 0.86)
- Optimizing $(L_0, L_1)$-Smooth Functions by Gradient Methods (ICLR 2025 · similarity 0.86)
- Efficiently Escaping Saddle Points under Generalized Smoothness via Self-Bounding Regularity (NeurIPS 2025 · similarity 0.85)
- Generalized Smooth Variational Inequalities: Methods with Adaptive Stepsizes (ICML 2024 · 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.