AI Paper Atlas

Research map / Federated learning and privacy / Differential privacy

A Randomized Approach to Tight Privacy Accounting

Jiachen T. Wang, Saeed Mahloujifar, Tong Wu, Ruoxi Jia, Prateek Mittal

NeurIPS 2023 · Federated learning and privacy › Differential privacy · approach: Private training with public data · 0 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 EVR with DP-SGD rather than relying directly on a strict upper boundFine-tuning ImageNet-pretrained BEiT · CIFAR100test error: around 7% (relative) error reduction when ε=0.6Improved
Use importance sampling for online privacy accountingMC accountant · Online accounting, (σ, δ, q) = (1.0, 10^{-9}, 10^{-3})relative errorImproved
Reuse previously drawn samples for each new composition stepMC accountant · Online privacy accountingruntime: around 5 times fasterImproved
Use GPU acceleration instead of CPU-only samplingMC sampling of Gaussian mixtures · Gaussian mixture samplingspeedup: 10^3 timesImproved
Use a higher τ in EVR verificationEVR · Composed Gaussian mechanismsprivacy bound tightnessImproved
Use a higher τ in EVR verificationEVR · Composed Gaussian mechanismsruntime: <2 minutesHurt
Replace simple Monte Carlo sampling with exponential-tilting importance sampling (ablation)MC estimator for Poisson Subsampled Gaussian composition · Privacy verificationestimator second momentImproved
Set θ to the proposed heuristic rather than θ=0 (ablation)Importance Sampling estimator · Poisson Subsampled Gaussian compositionestimator second momentImproved

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