Research map / Optimization / Nonconvex and smooth optimization
Private Adaptive Gradient Methods for Convex Optimization
Hilal Asi, John Duchi, Alireza Fallah, Omid Javidbakht, Kunal Talwar
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 PAGAN instead of DP-SGD | LSTM · WikiText-2 test, ε=3 | perplexity: 238.44 -> 224.82 | Improved |
| Use PAGAN instead of DP-SGD | LSTM · WikiText-2 test, ε=1 | perplexity: 285.11 -> 253.41 | Improved |
| Use PAGAN instead of DP-SGD | LSTM · WikiText-2 test, ε=.5 | perplexity: 350.23 -> 291.41 | Improved |
| Use PASAN instead of DP-SGD | LSTM · WikiText-2 test, ε=3 | perplexity: 238.44 -> 238.87 | No clear effect |
| Use PASAN instead of DP-SGD | LSTM · WikiText-2 test, ε=1 | perplexity: 285.11 -> 274.63 | Improved |
| Use PASAN instead of DP-SGD | LSTM · WikiText-2 test, ε=.5 | perplexity: 350.23 -> 332.52 | Improved |
| Adapt the private noise and gradient update to gradient geometry | PAGAN · Synthetic absolute regression | sample loss | Improved |
| Use isotropic noise with standard private AdaGrad instead of geometry-adaptive noise | Private AdaGrad · Synthetic absolute regression, ε=4 | convergence speed | Hurt |
| Use PAGAN instead of non-adaptive private methods | LSTM · WikiText-2 | perplexity | Improved |
Closest papers by meaning
- Differentially Private Adaptive Optimization with Delayed Preconditioners (ICLR 2023 · similarity 0.92)
- Private Stochastic Convex Optimization with Heavy Tails: Near-Optimality from Simple Reductions (NeurIPS 2024 · similarity 0.90)
- Differential Private Stochastic Optimization with Heavy-tailed Data: Towards Optimal Rates (AAAI 2025 · similarity 0.90)
- Differentially Private Optimization with Sparse Gradients (NeurIPS 2024 · similarity 0.90)
- Private Gradient Descent for Linear Regression: Tighter Error Bounds and Instance-Specific Uncertainty Estimation (ICML 2024 · similarity 0.90)
- Faster Algorithms for User-Level Private Stochastic Convex Optimization (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.
