7 papers
Optimal Regularization for Performative Learning
Edwige Cyffers, Alireza Mirrokni, Marco Mondelli
In performative learning, the data distribution reacts to the deployed model - for example, because strategic users adapt their features to game it - which creates a more complex d…
Limits of Personalizing Differential Privacy Budgets
Edwige Cyffers, Juba Ziani
A key technical difficulty in differential privacy is selecting a privacy budget that satisfies privacy requirements while maximizing utility. A natural and well-studied workaround…
Unified Privacy Guarantees for Decentralized Learning via Matrix Factorization
Aurélien Bellet, Edwige Cyffers, Davide Frey +3
Decentralized Learning (DL) enables users to collaboratively train models without sharing raw data by iteratively averaging local updates with neighbors in a network graph. This se…
Setting is not the Issue in Differential Privacy
Edwige Cyffers
This position paper argues that setting the privacy budget in differential privacy should not be viewed as an important limitation of differential privacy compared to alternative m…
DP-MicroAdam: Private and Frugal Algorithm for Training and Fine-tuning
Mihaela HudiÅteanu, Nikita P. Kalinin, Edwige Cyffers
Adaptive optimizers are the de facto standard in non-private training as they often enable faster convergence and improved performance. In contrast, differentially private (DP) tra…
Fedivertex: a Graph Dataset based on Decentralized Social Networks for Trustworthy Machine Learning
Marc Damie, Edwige Cyffers
Decentralized machine learning - where each client keeps its own data locally and uses its own computational resources to collaboratively train a model by exchanging peer-to-peer m…