JMLR

Minimax density estimation in the adversarial framework under local differential privacy

Authors
M{\'{e}}lisande Albert Juliette Chevallier B{\'{e}}atrice Laurent Ousmane Sacko
Paper Information
  • Journal:
    Journal of Machine Learning Research
  • Added to Tracker:
    Jul 06, 2026
Abstract

We consider the problem of nonparametric density estimation under privacy constraints in an adversarial framework. To this end, we study minimax rates over Sobolev spaces under local differential privacy. We first obtain a lower bound which allows us to quantify the impact of privacy compared with the classical framework. Next, we introduce a new Coordinate block privacy mechanism that guarantees local differential privacy, which, coupled with a projection estimator, achieves the minimax optimal rates. Finally, we develop an adaptive procedure which is optimal in the minimax sense up to logarithmic terms.

Author Details
M{\'{e}}lisande Albert
Author
Juliette Chevallier
Author
B{\'{e}}atrice Laurent
Author
Ousmane Sacko
Author
Citation Information
APA Format
M{\'{e}}lisande Albert , Juliette Chevallier , B{\'{e}}atrice Laurent & Ousmane Sacko . Minimax density estimation in the adversarial framework under local differential privacy. Journal of Machine Learning Research .
BibTeX Format
@article{paper1428,
  title = { Minimax density estimation in the adversarial framework under local differential privacy },
  author = { M{\'{e}}lisande Albert and Juliette Chevallier and B{\'{e}}atrice Laurent and Ousmane Sacko },
  journal = { Journal of Machine Learning Research },
  url = { https://www.jmlr.org/papers/v27/24-0494.html }
}