Research map / Optimization / Nonconvex and smooth optimization
Private (Stochastic) Non-Convex Optimization Revisited: Second-Order Stationary Points and Excess Risks
Daogao Liu, Arun Ganesh, Sewoong Oh, Abhradeep Guha Thakurta
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 variance-reduced SpiderBoost-based private algorithm instead of prior private SOSP methods | Private SpiderBoost framework · Empirical alpha-SOSP (theory) | alpha-SOSP rate | Improved |
| Extend private SOSP guarantee from empirical to population risk | Private SpiderBoost framework · Population alpha-SOSP (theory) | alpha-SOSP rate | Improved |
| Use exponential mechanism in polynomial time instead of prior method | Exponential mechanism · Excess population risk, poly-time | excess risk bound | Improved |
| Allow exponential time for the exponential mechanism | Exponential mechanism · Excess population risk, exp-time | excess risk bound | Improved |
Closest papers by meaning
- Second-Order Convergence in Private Stochastic Non-Convex Optimization (NeurIPS 2025 · similarity 0.91)
- Improved Sample Complexity for Private Nonsmooth Nonconvex Optimization (ICML 2025 · similarity 0.91)
- Differential Private Stochastic Optimization with Heavy-tailed Data: Towards Optimal Rates (AAAI 2025 · similarity 0.90)
- Private Stochastic Convex Optimization with Heavy Tails: Near-Optimality from Simple Reductions (NeurIPS 2024 · similarity 0.90)
- Faster Algorithms for User-Level Private Stochastic Convex Optimization (NeurIPS 2024 · similarity 0.89)
- Private Zeroth-Order Nonsmooth Nonconvex Optimization (ICLR 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.
