Research map / Optimization / Nonconvex and smooth optimization
Faster Gradient-Free Algorithms for Nonsmooth Nonconvex Stochastic 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 |
|---|---|---|---|
| Replace single-sample zeroth-order estimates with recursive gradient estimates and periodic batch refreshes | GFM for nonsmooth nonconvex stochastic optimization · Nonsmooth nonconvex stochastic optimization | stochastic zeroth-order oracle complexity: \fO\left(d^{3/2} \left( \dfrac{ L^4 }{\epsilon^4} + \dfrac{ \Delta L^3 }{\delta \epsilon^4}\right) \right) -> \mathcal{O | Helped |
| Use recursive gradient estimation instead of the vanilla zeroth-order gradient estimator | GFM · Nonconvex penalized SVM | loss versus zeroth-order complexity | Helped |
| Use recursive gradient estimation instead of the vanilla zeroth-order gradient estimator | GFM · Black-box attack on CNN (MNIST, Fashion-MNIST) | attack success rate | Helped |
| Warm-start GFM+ with GFM to reduce the initial objective gap | GFM+ for nonsmooth convex optimization · Nonsmooth convex stochastic optimization | stochastic zeroth-order oracle complexity: \mathcal{O}\left( \frac{d^{3/2} L^3}{\epsilon^3} + \frac{d^{3/2} L^3 R}{\delta \epsilon^3} \right) -> \mathcal{O}\left( | Helped |
Closest papers by meaning
- Decentralized Gradient-Free Methods for Stochastic Non-smooth Non-convex Optimization (AAAI 2024 · similarity 0.90)
- Improved Sample Complexity for Private Nonsmooth Nonconvex Optimization (ICML 2025 · similarity 0.90)
- Zeroth-Order Methods for Constrained Nonconvex Nonsmooth Stochastic Optimization (ICML 2024 · similarity 0.90)
- Gradient-Free Methods for Nonconvex Nonsmooth Stochastic Compositional Optimization (NeurIPS 2024 · similarity 0.89)
- Stochastic Optimization with Random Search (NeurIPS 2026 · similarity 0.89)
- An Online Optimization Perspective on First-Order and Zero-Order Decentralized Nonsmooth Nonconvex Stochastic Optimization (ICML 2024 · similarity 0.89)
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.