Research map / Optimization / Nonconvex and smooth optimization
Gradientless Descent: High-Dimensional Zeroth-Order 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 |
|---|---|---|---|
| Project the HalfCheetah linear-policy state to 200 dimensions | GLD with a linear policy · HalfCheetah-v1 | maximum reward: 4064 -> 4342 | Helped |
| Use GLD-Fast rather than GLD-Search | GLD · BBOB benchmarks | optimality gap | Helped |
| Use GLD-Fast rather than ARS | zeroth-order optimization · high-dimensional quadratic objectives | optimality gap | Helped |
| Apply a monotone transformation to the objective | GLD · transformed quadratic objectives | convergence | No clear effect |
| Over-approximate the condition number supplied to GLD-Fast | GLD-Fast · quadratic objectives | optimality gap | Helped |
| Underestimate the condition number supplied to GLD-Fast | GLD-Fast · quadratic objectives | convergence | No clear effect |
Closest papers by meaning
- Zeroth-Order Optimization Finds Flat Minima (NeurIPS 2025 · similarity 0.89)
- Adaptively Incorporating Directional Hints into Zeroth-Order Optimization (NeurIPS 2026 · similarity 0.88)
- Gradient Compressed Sensing: A Query-Efficient Gradient Estimator for High-Dimensional Zeroth-Order Optimization (ICML 2024 · similarity 0.87)
- Revisiting Zeroth-Order Optimization: Minimum-Variance Two-Point Estimators and Directionally Aligned Perturbations (ICLR 2025 · similarity 0.87)
- Stability and Generalization of Zeroth-Order Decentralized Stochastic Gradient Descent with Changing Topology (AAAI 2025 · similarity 0.87)
- Toward a Unified Theory of Gradient Descent under Generalized Smoothness (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.
