AI Paper Atlas

Research map / Federated learning and privacy / Differential privacy

Private Federated Frequency Estimation: Adapting to the Hardness of the Instance

Jingfeng Wu, Wennan Zhu, Peter Kairouz, Vladimir Braverman

NeurIPS 2023 · Federated learning and privacy › Differential privacy · approach: Local-DP and private estimation · 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
set count sketch width by instance-optimal rule instead of minimax-optimal rule (ablation)count sketch, single round · Gowalla, C4, Sentiment-140sketch size for target l_inf errorImproved
set count sketch width with the two-phase method instead of minimax-optimal rule (ablation)count sketch, single round · Gowalla, C4, Sentiment-140sketch size for target l_inf errorImproved
use two-phase method (small sketch on n/10 clients to fit top-20 polynomial) versus instance-optimal oracle (ablation)count sketch, single round · Gowallasketch size for target l_inf errorNo clear effect
replace simple count sketch (SCS) with hybrid count sketch (HCS) for heavy-tailed homogeneous frequenciesmulti-round FFE · synthetic i^-1.1 and i^-2, d=10^5, M=10expected l_inf errorNo clear effect
use HCS instead of FCS and SCS for steeper power law (degree 3)multi-round FFE · synthetic homogeneous, M=10expected l_inf errorImproved
use hybrid or full count sketch instead of simple count sketch with heavy-tailed heterogeneitymulti-round FFE · Gowalla, M=10l_inf errorImproved
use HCS instead of FCS and SCS under moderately light tailsmulti-round FFE · C4, M=10estimate shape / errorImproved
use HCS in Sentiment-140 multi-round experimentmulti-round FFE · Sentiment-140, M=10errorImproved
average more rounds in homogeneous case with HCShybrid count sketch · homogeneous multi-round FFEerror scalingImproved

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