A unifying framework for differentially private sums under continual observation
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 any …
observation. We give a unifying framework and an efficient algorithm for this problem for any …
Efficient and near-optimal noise generation for streaming differential privacy
In the task of differentially private (DP) continual counting, we receive a stream of increments
and our goal is to output an approximate running total of these increments, without revealing …
and our goal is to output an approximate running total of these increments, without revealing …
Improved counting under continual observation with pure differential privacy
Counting under continual observation is a well-studied problem in the area of differential
privacy. Given a stream of updates $ x_1, x_2,\dots, x_T\in\{0, 1\} $ the problem is to …
privacy. Given a stream of updates $ x_1, x_2,\dots, x_T\in\{0, 1\} $ the problem is to …
Optimal Rates for DP-SCO with a Single Epoch and Large Batches
The most common algorithms for differentially private (DP) machine learning (ML) are all
based on stochastic gradient descent, for example, DP-SGD. These algorithms achieve DP …
based on stochastic gradient descent, for example, DP-SGD. These algorithms achieve DP …
Time-Aware Projections: Truly Node-Private Graph Statistics under Continual Observation
Releasing differentially private statistics about social network data is challenging: one
individual's data consists of a node and all of its connections, and typical analyses are …
individual's data consists of a node and all of its connections, and typical analyses are …
DPSW-Sketch: A Differentially Private Sketch Framework for Frequency Estimation over Sliding Windows
The sliding window model of computation captures scenarios in which data are continually
arriving in the form of a stream, and only the most recent w items are used for analysis. In …
arriving in the form of a stream, and only the most recent w items are used for analysis. In …
Adaptive Data Analysis for Growing Data
NG Marchant, BIP Rubinstein - arXiv preprint arXiv:2405.13375, 2024 - arxiv.org
Reuse of data in adaptive workflows poses challenges regarding overfitting and the
statistical validity of results. Previous work has demonstrated that interacting with data via …
statistical validity of results. Previous work has demonstrated that interacting with data via …
Continual Counting with Gradual Privacy Expiration
Differential privacy with gradual expiration models the setting where data items arrive in a
stream and at a given time $ t $ the privacy loss guaranteed for a data item seen at time $(td) …
stream and at a given time $ t $ the privacy loss guaranteed for a data item seen at time $(td) …
Concurrent Composition for Continual Mechanisms
M Henzinger, R Safavi, S Vadhan - arXiv preprint arXiv:2411.03299, 2024 - arxiv.org
A series of recent works by Lyu, Wang, Vadhan, and Zhang (TCC21, NeurIPS22, STOC23)
showed that composition theorems for non-interactive differentially private mechanisms …
showed that composition theorems for non-interactive differentially private mechanisms …