AI Paper Atlas

Research map / Federated learning and privacy / Differential privacy

Functional Renyi Differential Privacy for Generative Modeling

Dihong Jiang, Sun Sun, Yaoliang Yu

NeurIPS 2023 · Federated learning and privacy › Differential privacy · approach: Private data analysis frameworks · 5 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
use f-RDP kernel method instead of SoTA DPDM at eps=0.2DP-kernel (conditional) · MNIST eps=0.2FID: 61.9 -> 26.5Improved
use f-RDP kernel method instead of SoTA DPDM at eps=0.2DP-kernel (conditional) · FMNIST eps=0.2FID: 78.4 -> 46.2Improved
use f-RDP kernel method instead of DP-MERF at eps=0.2DP-kernel (conditional) · CelebA eps=0.2FID: 264.8 -> 85.9Improved
use f-RDP kernel method instead of DP-MERF at eps=0.2DP-kernel (conditional) · CelebA eps=0.2accuracy: 52.7 -> 86.5Improved
use f-RDP kernel method instead of DPDM at eps=0.2DP-kernel (conditional) · MNIST eps=0.2accuracy: 71.9 -> 91.3Improved
compare with DPDM at eps=1DP-kernel (conditional) · MNIST eps=1FID: 23.4 -> 29.5No clear effect
parallel per-class sub-models instead of conditional generator (ablation)DP-kernel · MNIST eps=1FID: 29.5 -> 21.8Improved
parallel per-class sub-models instead of conditional generator (ablation)DP-kernel · MNIST eps=0.2FID: 26.5 -> 37.3Hurt
parallel per-class sub-models instead of conditional generator (ablation)DP-kernel · CelebA eps=0.2FID: 85.9 -> 95.8Hurt
parallel per-class sub-models instead of conditional generator (ablation)DP-kernel · MNIST eps=0.2accuracy: 91.3 -> 93.7Improved
parallel per-class sub-models instead of conditional generator (ablation)DP-kernel · CelebA eps=10FID: 77.2 -> 78.5No clear effect
lower privacy budget eps from 1 to 0.2DP-kernel (conditional) · MNISTaccuracy: 93.4 -> 91.3Hurt

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