Showing 2026Show all
2 papers · 1 filter
cs.CR2026
Optimal Conversion from Zero-Concentrated to Gaussian Differential Privacy
Yu-Wei Chen, Aaradhya Pandey, Jordan Awan
Gaussian differential privacy (GDP) and zero-concentrated differential privacy (zCDP) are two competing privacy accounting frameworks, but they share similar minimax lower bounds i…
math.ST2026
Statistical Unlearning of Distributions: A Hypothesis Testing Approach
Aaradhya Pandey, Sanjeev Kulkarni
Machine learning systems increasingly face requirements to forget not only individual data points, but entire domains of information, such as toxic language, copyrighted corpora, o…