AI Paper Atlas

Research map / Federated learning and privacy / Differential privacy

Permute-and-Flip: A new mechanism for differentially private selection

Ryan McKenna, Daniel R. Sheldon

NeurIPS 2020 · Federated learning and privacy › Differential privacy · approach: Privacy accounting and mechanisms · 20 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
Sample candidates without replacement rather than with replacementPermute-and-Flip versus Exponential Mechanism · Differentially private selection, all score vectorsexpected error: up to two times lowerImproved
Sample candidates without replacement rather than with replacementPermute-and-Flip versus Exponential Mechanism · HEPTH mode selection at ε=0.04expected error: 1.84Improved
Sample candidates without replacement rather than with replacementPermute-and-Flip versus Exponential Mechanism · HEPTH median selection at ε=0.01expected error: 1.93Improved
Use Permute-and-Flip instead of the optimal regular mechanismPermute-and-Flip · Bounded 2Δ-lattice, ε ≥ log(½(3 + √5))average expected errorNo clear effect

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