AI Paper Atlas

Research map / Federated learning and privacy / Differential privacy

Efficient privacy loss accounting for subsampling and random allocation

Vitaly Feldman, Moshe Shenfeld

ICML 2026 · Federated learning and privacy › Differential privacy · approach: Privacy accounting and mechanisms · 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 the PLD-based random allocation accounting instead of prior analytic bounds (hockey-stick and Renyi based)1-out-of-t random allocation with Gaussian mechanism · Gaussian mechanism, delta = 10^-6, varying sigma and tprivacy parameter epsilonImproved
compare PLD-based bound to Monte Carlo estimatesrandom allocation privacy profile · Chua et al. 2024a settingprivacy profileImproved
use random allocation instead of Poisson sampling at same noise and expected batch size (Gaussian)DP-SGD privacy accounting · nearly all parameter regimesprivacy profileImproved
use random allocation instead of Poisson sampling when epsilon is much smaller than 1Gaussian mechanism · epsilon << 1privacy profileMixed
use random allocation instead of Poisson sampling with Laplace mechanismLaplace mechanism · varying sigma and tprivacy guaranteeMixed
use PLD accounting instead of RDP-based accounting for DP-SGD with PREAMBLEPREAMBLE (n=6e5, d=2^20, C=2^15, E=10) · (epsilon=1, delta=10^-6)noise ratio sigma vs plain Gaussian DP-SGDImproved
use random allocation instead of Poisson subsampling in synthetic Bernoulli mean estimationnoisy sum estimation · Feldman & Shenfeld 2025 toy exampleaccuracy at fixed privacyImproved
decrease discretization parameter alpha (ablation)PLD random allocation algorithm · runtime on laptopruntimeHurt

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