Research map / Optimization / Nonconvex and smooth optimization
Faster Rates of Differentially Private Stochastic Convex Optimization
Jinyan Su, Lijie Hu, Di Wang
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 Iterated SGD with theta-bar 1.5 instead of 2 (ablation) | Iterated Phased-SGD · l2-regularized logistic regression, libsvm datasets | testing error | Improved |
| Iterated SGD versus Phased-SGD-SC | Iterated Phased-SGD · l2-regularized logistic regression, a8a a9a ijcnn1 w7a | testing error | Improved |
| Iterated SGD versus DP-SGD and SC-psgd | Iterated Phased-SGD · l2-regularized logistic regression, a8a a9a ijcnn1 w7a | testing error | Hurt |
| PSA versus Iterated SGD | PSA · linear regression, l1 ball | testing error | Improved |
| PSA versus Iterated SGD on IJCNN | PSA · IJCNN privacy budget sweep | testing error | Hurt |
| PSA versus baselines at small epsilon | PSA · l4-norm linear regression, small epsilon | testing error | Mixed |
Closest papers by meaning
- Differential Private Stochastic Optimization with Heavy-tailed Data: Towards Optimal Rates (AAAI 2025 · similarity 0.93)
- Private Stochastic Convex Optimization with Heavy Tails: Near-Optimality from Simple Reductions (NeurIPS 2024 · similarity 0.92)
- Faster Algorithms for User-Level Private Stochastic Convex Optimization (NeurIPS 2024 · similarity 0.92)
- Public-data Assisted Private Stochastic Optimization: Power and Limitations (NeurIPS 2024 · similarity 0.89)
- Differentially Private Optimization with Sparse Gradients (NeurIPS 2024 · similarity 0.89)
- Improved Differentially Private and Lazy Online Convex Optimization: Lower Regret without Smoothness Requirements (ICML 2024 · 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.
