BARC talk by Christian Lebeda
Wednesday, April 16, 2025, Christian Lebeda, now a postdoc at Inria, Montpellier, France, will give a talk on "Better Gaussian Mechanism using Correlated Noise".
Abstract:
Privately answering aggregate queries is a common task in differentially private data analysis. The Gaussian Mechanism is the standard technique for this problem, protecting privacy by independently adding Gaussian noise to each query. In this talk I show that, under the add/remove variant of differential privacy, the magnitude of noise can be reduced by almost half by introducing a small amount of correlated noise. The algorithm is extremely simple, requiring only a minor change to the standard approach. The underlying idea can be adapted to other settings to achieve similar improvements.
Bio:
Christian is a postdoc working with Aurélien Bellet in the PreMeDICaL Team, Inria, Montpellier. His research focuses on several topics within the field of differential privacy. Relevant to this talk, he is interested in understanding the structure of queries with the goal of improving additive noise mechanisms. Before joining Inria as a postdoc, Christian completed his PhD from 2020 to 2023 at ITU and BARC with Rasmus Pagh and Martin Aumüller. From 2023 to 2024, he was a postdoc at ITU.
Host:
Rasmus Pagh