AI Paper Atlas

Research map / Federated learning and privacy / Differential privacy

Improving Noise Efficiency in Privacy-preserving Dataset Distillation

Runkai Zheng, Vishnu Asutosh Dasu, Yinong Oliver Wang, Haohan Wang, Fernando De La Torre

ICCV 2025 · Federated learning and privacy › Differential privacy · approach: Differentially private synthetic data · 4 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
add DOS (decoupled sampling and optimization) to the baseline (ablation)Dosser · CIFAR-10 (IPC=10, eps=1)accuracy: 41.7 -> 47.7Improved
add SER (subspace projection) to the baseline (ablation)Dosser · CIFAR-10 (IPC=10, eps=1)accuracy: 41.7 -> 46.5Improved
add SER on top of DOS (ablation)Dosser · CIFAR-10 (IPC=10, eps=1)accuracy: 47.7 -> 50.6Improved
add SER when privacy noise is small (eps=10) (ablation)Dosser · CIFAR-10 (IPC=50, eps=10)accuracy: 57.7 -> 57.6No clear effect
add SER on top of DOS at eps=10, IPC=50 (ablation)Dosser · CIFAR-10 (IPC=50, eps=10)accuracy: 61.1 -> 61.0No clear effect
increase optimization iterations beyond sampling iterations (DOS) (ablation)Dosser · CIFAR-10accuracyImproved
vary auxiliary dataset size in SER (ablation)Dosser · CIFAR-10accuracyNo clear effect
use full 2048-dim PCA projection instead of no SER (ablation)Dosser · CIFAR-10accuracyImproved
add PEA augmentation to DosserDosser · CIFAR-10 IPC=10 (eps=1)accuracy: 44.2 -> 50.6Improved
add PEA augmentation to DosserDosser · FashionMNIST IPC=10 (eps=1)accuracy: 81.6 -> 80.1Hurt
replace NDPDC with Dosser (DOS+SER)NDPDC · CIFAR-10 IPC=10 (eps=1)accuracy: 39.4 -> 44.2Improved
run DP-PCA per iteration instead of fixed auxiliary-data projectionDosser · CIFAR-10accuracyHurt

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