Research map / Optimization / Nonconvex and smooth optimization
Differentially Private Stochastic Optimization: New Results in Convex and Non-Convex Settings
Raef Bassily, Cristóbal A Guzmán, Michael Menart
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 |
|---|---|---|---|
| Approximate Moreau envelope of generalized linear loss to smooth it, then use DP-SCO smooth algorithm in l2 | DP-SCO for non-smooth GLL · l2 setting | running time | Improved |
| Use noisy Frank-Wolfe with Rademacher generalization bounds for GLL in l1 | DP-SCO non-smooth GLL · l1 setting | excess risk | Improved |
| Use variance-reduced stochastic Frank-Wolfe with round scheduling for non-convex smooth losses | private non-convex SO · l1 setting | stationarity rate | Improved |
| Linear-time l2 algorithm versus prior superlinear unconstrained method | private non-convex SO · l2 setting | stationarity rate | Mixed |
Closest papers by meaning
- Private Stochastic Convex Optimization with Heavy Tails: Near-Optimality from Simple Reductions (NeurIPS 2024 · similarity 0.92)
- Differential Private Stochastic Optimization with Heavy-tailed Data: Towards Optimal Rates (AAAI 2025 · similarity 0.91)
- Faster Algorithms for User-Level Private Stochastic Convex Optimization (NeurIPS 2024 · similarity 0.90)
- Improved Sample Complexity for Private Nonsmooth Nonconvex Optimization (ICML 2025 · similarity 0.90)
- Improved Differentially Private and Lazy Online Convex Optimization: Lower Regret without Smoothness Requirements (ICML 2024 · similarity 0.89)
- Differentially Private Optimization with Sparse Gradients (NeurIPS 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.
