Research map / Optimization / Nonconvex and smooth optimization
Iterative Linearized Control: Stable Algorithms and Complexity Guarantees
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 |
|---|---|---|---|
| Adding a proximal regularization term to the Gauss-Newton (ILQR) step, giving regularized ILQR (RegILQR) | ILQR / Gauss-Newton control steps · inverted pendulum and two-links arm control problems (horizon 100) | function value and gradient norm convergence | Helped |
| Adding Catalyst-style extrapolation step to regularized Gauss-Newton (accelerated regularized ILQR) | Regularized ILQR · inverted pendulum and two-links arm control problems (horizon 100) | function value and gradient norm convergence | Helped |
| Using a regularized Gauss-Newton step instead of plain Gauss-Newton (ILQR) in the composite setting | Nonlinear control with composite objective · theoretical complexity | global convergence rate to stationary point | Helped |
| Using a line-search (Armijo) on ILQR steps | ILQR · inverted pendulum and two-links arm | convergence | No clear effect |
Closest papers by meaning
- Constrained Optimization From a Control Perspective via Feedback Linearization (NeurIPS 2025 · similarity 0.88)
- Breaking the Convergence Barrier: Optimization via Fixed-Time Convergent Flows (AAAI 2022 · similarity 0.87)
- Global Convergence of Online Optimization for Nonlinear Model Predictive Control (NeurIPS 2021 · similarity 0.86)
- The Power of Learned Locally Linear Models for Nonlinear Policy Optimization (ICML 2023 · similarity 0.86)
- Differentiable Nonlinear Model Predictive Control (NeurIPS 2026 · similarity 0.85)
- A Regularized Newton Method for Nonconvex Optimization with Global and Local Complexity Guarantees (NeurIPS 2025 · similarity 0.84)
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.