Researchers have developed a new quadrature method that significantly accelerates privacy accounting for the U.S. Decennial Census. This method, leveraging sieve algorithms and the discrete Fourier transform, achieves an 1,824-fold speedup over previous techniques while adhering to strict error tolerances. The innovation allows for more precise determination of the minimum noise needed for differential privacy, thereby enhancing the statistical utility of census data for applications like federal funding allocation and political redistricting. AI
IMPACT Enhances statistical utility of census data by enabling more precise privacy guarantees, potentially improving downstream applications.
RANK_REASON This is a research paper detailing a new computational method for privacy accounting in census data. [lever_c_demoted from research: ic=2 ai=0.4]
- Demographic and Housing Characteristics File
- discrete Fourier transform
- discrete Gaussian mechanisms
- Gaussian noise
- Sieve algorithms for the shortest vector problem are practical
- trapezoidal rule
- United States Census Bureau
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →
