Differentially Private Medians and Interior Points for Non-Pathological Data Article Swipe
Related Concepts
Estimator
Contrast (vision)
Mathematics
Sample (material)
Construct (python library)
Distribution (mathematics)
Moment (physics)
Statistics
Combinatorics
Median
Large sample
Mathematical analysis
Computer science
Physics
Geometry
Artificial intelligence
Thermodynamics
Classical mechanics
Programming language
Maryam Aliakbarpour
,
Rose Silver
,
Thomas Steinke
,
Jonathan Ullman
·
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.4230/lipics.itcs.2024.3
· OA: W4378072601
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.4230/lipics.itcs.2024.3
· OA: W4378072601
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.
Related Topics
Finding more related topics…