5 papers
Minimax Private Estimation of Smooth Optimal-Transport Maps
Clément Lalanne, David Rodríguez-Vítores, Franck Iutzeler +1
We study the problem of estimating smooth optimal transport (OT) maps between two probability distributions under differential privacy (DP) constraints. Leveraging wavelet-based de…
Token-Efficient Change Detection in LLM APIs
Timothée Chauvin, Clément Lalanne, Erwan Le Merrer +3
Remote change detection in LLMs is a difficult problem. Existing methods are either too expensive for deployment at scale, or require initial white-box access to model weights or g…
On the Private Estimation of Smooth Transport Maps
Clément Lalanne, Franck Iutzeler, Jean-Michel Loubes +1
Estimating optimal transport maps between two distributions from respective samples is an important element for many machine learning methods. To do so, rather than extending discr…
Learning with Differentially Private (Sliced) Wasserstein Gradients
David Rodríguez-Vítores, Clément Lalanne, Jean-Michel Loubes
In this work, we introduce a novel framework for privately optimizing objectives that rely on Wasserstein distances between data-dependent empirical measures. Our main theoretical…
Privately Learning Smooth Distributions on the Hypercube by Projections
Clément Lalanne, Sébastien Gadat
Fueled by the ever-increasing need for statistics that guarantee the privacy of their training sets, this article studies the centrally-private estimation of Sobolev-smooth densiti…