26 citations · 48 across the 12 of their papers we have counts for
3 papers · 1 filter
A Unifying Framework for Differentially Private Sums under Continual Observation
Monika Henzinger, Jalaj Upadhyay, Sarvagya Upadhyay
We study the problem of maintaining a differentially private decaying sum under continual observation. We give a unifying framework and an efficient algorithm for this problem for…
Almost Tight Error Bounds on Differentially Private Continual Counting
Monika Henzinger, Jalaj Upadhyay, Sarvagya Upadhyay
The first large-scale deployment of private federated learning uses differentially private counting in the continual release model as a subroutine (Google AI blog titled "Federated…
A Framework for Private Matrix Analysis
Jalaj Upadhyay, Sarvagya Upadhyay
We study private matrix analysis in the sliding window model where only the last updates to matrices are considered useful for analysis. We give first efficient space di…