3 papers
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…
math.ST2025
Infinitely divisible privacy and beyond I: resolution of the conjecture
Aaradhya Pandey, Arian Maleki, Sanjeev Kulkarni
Differential privacy is increasingly formalized through the lens of hypothesis testing via the robust and interpretable -DP framework, where privacy guarantees are encoded by a…
stat.ML2025
Gaussian Certified Unlearning in High Dimensions: A Hypothesis Testing Approach
Aaradhya Pandey, Arnab Auddy, Haolin Zou +2
Machine unlearning seeks to efficiently remove the influence of selected data while preserving generalization. Significant progress has been made in low dimensions , but…