Research map / Federated learning and privacy / Differential privacy
Practical Differentially Private Hyperparameter Tuning with Subsampling
Antti Koskela, Tejas Kulkarni
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 |
|---|---|---|---|
| Tune hyperparameters on a random subset and transfer them to final-model training | DP-SGD and DP-Adam · CIFAR-10, MNIST, FashionMNIST, and IMDB | privacy-utility trade-off | Improved |
| Tune hyperparameters on a random subset and transfer them to final-model training | DP-SGD and DP-Adam · CIFAR-10, MNIST, FashionMNIST, and IMDB | computational cost | Improved |
| Use variant 1, training the final model on the data outside the tuning subset, rather than variant 2, which uses the full dataset | Subset tuning with DP-SGD · Classification benchmarks | test accuracy | Improved |
| Keep the learning rate fixed when transferring DP-Adam hyperparameters rather than scaling it with dataset size (ablation) | DP-Adam · Neural-network classification | test accuracy | Improved |
Closest papers by meaning
- Towards hyperparameter-free optimization with differential privacy (ICLR 2025 · similarity 0.91)
- Online Sensitivity Optimization in Differentially Private Learning (AAAI 2024 · similarity 0.90)
- Auditing Private Prediction (ICML 2024 · similarity 0.88)
- A New Linear Scaling Rule for Private Adaptive Hyperparameter Optimization (ICML 2024 · similarity 0.88)
- Differentially Private Model Merging (NeurIPS 2026 · similarity 0.88)
- Differentially Private Stochastic Gradient Descent with Fixed-Size Minibatches: Tighter RDP Guarantees with or without Replacement (NeurIPS 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.
