Research map / Optimization / Nonconvex and smooth optimization
Oracle Complexity in Nonsmooth Nonconvex Optimization
Guy Kornowski, Ohad Shamir
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 any local-oracle algorithm to seek points near approximately stationary points | Lipschitz bounded-below nonconvex functions · Lipschitz bounded-below nonconvex functions | iterations required for worst-case guarantees: exponential dependence on $d$ | Hurt |
| Apply randomized smoothing | 1-Lipschitz nonsmooth nonconvex functions · 1-Lipschitz nonsmooth nonconvex functions | gradient Lipschitz parameter: $\frac{c \sqrt{d}}{\epsilon}$ | Mixed |
| Use Lasry-Lions regularization instead of computationally efficient smoothing | 1-Lipschitz nonsmooth nonconvex functions · 1-Lipschitz nonsmooth nonconvex functions | gradient Lipschitz parameter: $\frac{c}{\epsilon}$ | Improved |
Closest papers by meaning
- Generalized-Smooth Nonconvex Optimization is As Efficient As Smooth Nonconvex Optimization (ICML 2023 · similarity 0.91)
- Faster Gradient-Free Algorithms for Nonsmooth Nonconvex Stochastic Optimization (ICML 2023 · similarity 0.90)
- An Online Optimization Perspective on First-Order and Zero-Order Decentralized Nonsmooth Nonconvex Stochastic Optimization (ICML 2024 · similarity 0.88)
- Escaping saddle points without Lipschitz smoothness: the power of nonlinear preconditioning (NeurIPS 2025 · similarity 0.87)
- Improved Sample Complexity for Private Nonsmooth Nonconvex Optimization (ICML 2025 · similarity 0.87)
- Efficiently Escaping Saddle Points under Generalized Smoothness via Self-Bounding Regularity (NeurIPS 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.
