articleMay 31, 2009Closed access
Differential privacy and robust statistics
Microsoft (United States) · University of California, Berkeley
Indexed incrossref
Abstract
We show by means of several examples that robust statistical estimators present an excellent starting point for differentially private estimators. Our algorithms use a new paradigm for differentially private mechanisms, which we call Propose-Test-Release (PTR), and for which we give a formal definition and general composition theorems.
Citation impact
630
total citations
- FWCI
- 26.71
- Percentile
- 100%
- References
- 22
Citations per year
Authors
2Topics & keywords
Topics
Keywords
- Differential privacy
- Estimator
- Computer science
- Robust statistics
- Differential (mechanical device)
- Point (geometry)
- Theoretical computer science
- Statistics
No related works found for this paper.