arXiv Machine Learning By Konstantina Bairaktari, Kasper Green Larsen

The Binary Tree Mechanism is Optimal for Approximate Differentially Private Continual Counting

Read the original on arXiv Machine Learning →

arXiv:2607. 00876v1 Announce Type: cross Abstract: Private continual counting is a fundamental problem in differential privacy: given a binary stream of length $n$, where each $1$ corresponds to the contribution of one individual, the goal is to release all running counts while protecting the privacy of each individual.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning
1d ago

Differentially Private Verification of Distribution Properties

arXiv:2604. 10819v2 Announce Type: replace-cross Abstract: A recent line of work initiated by Chiesa and Gur and further developed by Herman and Rothblum investigates the sample and communication complexity of verifying properties of distributions with the assistance of a powerful, knowledgeable, but untrusted prover.

By Elbert Du, Cynthia Dwork, Pranay Tankala, Linjun Zhang