Research map / Optimization / Nonconvex and smooth optimization
Optimal Stochastic Non-smooth Non-convex Optimization through Online-to-Non-convex Conversion
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 |
|---|---|---|---|
| Online-to-non-convex conversion with OGD (shifting regret via resets) instead of prior stochastic method | stochastic non-smooth non-convex optimization · (δ,ϵ)-stationary point | stochastic gradient complexity: O(ϵ^-4 δ^-1) to O(ϵ^-3 δ^-1) | Helped |
| Using optimistic online learning with careful hints (Algorithm 2) in deterministic second-order smooth setting | deterministic / second-order smooth objectives · (δ,ϵ)-stationary point | gradient complexity: from O(ϵ^-5/3 δ^-1/3) (Thm 16) to Õ(ϵ^-3/2 δ^-1/2) | Helped |
| Randomized scaling sn vs fixed sn=1/2 in deterministic setting | optimistic online reduction · deterministic smooth objectives | gradient complexity | No clear effect |
| Lower bound construction showing optimality of O(ϵ^-3 δ^-1) | stochastic non-smooth non-convex optimization · (δ,ϵ)-stationary point | query lower bound | No clear effect |
Closest papers by meaning
- High-Probability Bound for Non-Smooth Non-Convex Stochastic Optimization with Heavy Tails (ICML 2024 · similarity 0.91)
- An Online Optimization Perspective on First-Order and Zero-Order Decentralized Nonsmooth Nonconvex Stochastic Optimization (ICML 2024 · similarity 0.91)
- Complexity Lower Bounds of Adaptive Gradient Algorithms for Non-convex Stochastic Optimization under Relaxed Smoothness (ICLR 2025 · similarity 0.89)
- Gradient-Variation Online Adaptivity for Accelerated Optimization with Hölder Smoothness (NeurIPS 2025 · similarity 0.89)
- Stochastic Zeroth-Order Optimization under Strongly Convexity and Lipschitz Hessian: Minimax Sample Complexity (NeurIPS 2024 · similarity 0.89)
- Optimistic Online-to-Batch Conversions for Accelerated Convergence and Universality (NeurIPS 2025 · 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.