Differentially Private Medians and Interior Points for Non-Pathological Data
Date
2024
Journal Title
Journal ISSN
Volume Title
Publisher
Schloss Dagstuhl - Leibniz Center for Informatics
Abstract
We construct sample-efficient differentially private estimators for the approximate-median and interior-point problems, that can be applied to arbitrary input distributions over ℝ satisfying very mild statistical assumptions. Our results stand in contrast to the surprising negative result of Bun et al. (FOCS 2015), which showed that private estimators with finite sample complexity cannot produce interior points on arbitrary distributions.
Description
Advisor
Degree
Type
Journal article
Keywords
Citation
Aliakbarpour, M., Silver, R., Steinke, T., & Ullman, J. (2024). Differentially Private Medians and Interior Points for Non-Pathological Data. DROPS-IDN/v2/Document/10.4230/LIPIcs.ITCS.2024.3. 15th Innovations in Theoretical Computer Science Conference (ITCS 2024). https://doi.org/10.4230/LIPIcs.ITCS.2024.3
Has part(s)
Forms part of
Published Version
Rights
Except where otherwise noted, this work is licensed under a Creative Commons Attribution (CC BY) license. Permission to reuse, publish, or reproduce the work beyond the terms of the license or beyond the bounds of fair use or other exemptions to copyright law must be obtained from the copyright holder.