Research map / Optimization / Nonconvex and smooth optimization
Fast Gradient-Based Methods with Exponential Rate: A Hybrid Control Framework
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 a larger discrete step size s=1.65/Lf instead of the Corollary 3.9 step size s=1/Lf (ablation) | Hybrid discrete algorithm (Algorithm 1) · Quadratic f, n=5 | suboptimality decay f(x_k)-f* | Helped |
| Increase NSR minimum restart interval kmin from 1 to 6 or 7 (ablation) | Nesterov with speed restarting (NSR) · Quadratic f, n=5 | monotonicity of suboptimality | Hurt |
| Use the state-dependent damping feedback with hybrid restarts (proposed) instead of time-dependent damping with speed restart | Fast gradient method · Quadratic f, n=5 | monotonicity of suboptimality | Helped |
Closest papers by meaning
- Convergence-Rate-Matching Discretization of Accelerated Optimization Flows Through Opportunistic State-Triggered Control (NeurIPS 2019 · similarity 0.88)
- A Unified Discretization Framework for Differential Equation Approach with Lyapunov Arguments for Convex Optimization (NeurIPS 2023 · similarity 0.86)
- Constrained Optimization From a Control Perspective via Feedback Linearization (NeurIPS 2025 · similarity 0.85)
- Accelerating Optimization via Differentiable Stopping Time (NeurIPS 2025 · similarity 0.83)
- Neural Time-Reversed Generalized Riccati Equation (AAAI 2024 · similarity 0.83)
- FESSNC: Fast Exponentially Stable and Safe Neural Controller (ICML 2024 · similarity 0.83)
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.