AI Paper Atlas

Research map / Federated learning and privacy / Differential privacy

Practical Differentially Private Hyperparameter Tuning with Subsampling

Antti Koskela, Tejas Kulkarni

NeurIPS 2023 · Federated learning and privacy › Differential privacy · approach: DP-SGD refinements · 3 citations (OpenAlex)

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 changedWhereMeasuredEffect
Tune hyperparameters on a random subset and transfer them to final-model trainingDP-SGD and DP-Adam · CIFAR-10, MNIST, FashionMNIST, and IMDBprivacy-utility trade-offImproved
Tune hyperparameters on a random subset and transfer them to final-model trainingDP-SGD and DP-Adam · CIFAR-10, MNIST, FashionMNIST, and IMDBcomputational costImproved
Use variant 1, training the final model on the data outside the tuning subset, rather than variant 2, which uses the full datasetSubset tuning with DP-SGD · Classification benchmarkstest accuracyImproved
Keep the learning rate fixed when transferring DP-Adam hyperparameters rather than scaling it with dataset size (ablation)DP-Adam · Neural-network classificationtest accuracyImproved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy