Research map / Optimization / Nonconvex and smooth optimization
Differentially Private Empirical Risk Minimization with Smooth Non-Convex Loss Functions: A Non-Stationary View
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 |
|---|---|---|---|
| use zCDP-based noise calibration instead of moments accountant or advanced composition constants | DP-GD / DP-PGD · Covertype and synthetic, sigmoid loss with l1 regularizer | l2 norm of projected gradient | Helped |
| increase privacy budget epsilon (ablation) | DP-GD · Covertype and synthetic | l2 norm of gradient | Helped |
| increase sample size n (ablation) | DP-GD · Covertype and synthetic | l2 norm of gradient | Helped |
| increase iteration number T (ablation) | DP-GD · Covertype and synthetic | l2 norm of gradient | No clear effect |
Closest papers by meaning
- Differentially Private Optimization with Sparse Gradients (NeurIPS 2024 · similarity 0.90)
- Adapting to Linear Separable Subsets with Large-Margin in Differentially Private Learning (ICML 2025 · similarity 0.89)
- Improved Sample Complexity for Private Nonsmooth Nonconvex Optimization (ICML 2025 · similarity 0.89)
- Improved Rates of Differentially Private Nonconvex-Strongly-Concave Minimax Optimization (AAAI 2025 · similarity 0.89)
- Faster Algorithms for User-Level Private Stochastic Convex Optimization (NeurIPS 2024 · similarity 0.88)
- Differential Private Stochastic Optimization with Heavy-tailed Data: Towards Optimal Rates (AAAI 2025 · similarity 0.88)
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.