Certified private data release for sparse Lipschitz functions

Konstantin Donhauser, Johan Lokna, Amartya Sanyal, March Boedihardjo, Robert Hönig, Fanny Yang
Proceedings of The 27th International Conference on Artificial Intelligence and Statistics, PMLR 238:1396-1404, 2024.

Abstract

As machine learning has become more relevant for everyday applications, a natural requirement is the protection of the privacy of the training data. When the relevant learning questions are unknown in advance, or hyper-parameter tuning plays a central role, one solution is to release a differentially private synthetic data set that leads to similar conclusions as the original training data. In this work, we introduce an algorithm that enjoys fast rates for the utility loss for sparse Lipschitz queries. Furthermore, we show how to obtain a certificate for the utility loss for a large class of algorithms.

Cite this Paper

BibTeX
@InProceedings{pmlr-v238-donhauser24a, title = {Certified private data release for sparse {L}ipschitz functions}, author = {Donhauser, Konstantin and Lokna, Johan and Sanyal, Amartya and Boedihardjo, March and H\"{o}nig, Robert and Yang, Fanny}, booktitle = {Proceedings of The 27th International Conference on Artificial Intelligence and Statistics}, pages = {1396--1404}, year = {2024}, editor = {Dasgupta, Sanjoy and Mandt, Stephan and Li, Yingzhen}, volume = {238}, series = {Proceedings of Machine Learning Research}, month = {02--04 May}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v238/donhauser24a/donhauser24a.pdf}, url = {https://proceedings.mlr.press/v238/donhauser24a.html}, abstract = {As machine learning has become more relevant for everyday applications, a natural requirement is the protection of the privacy of the training data. When the relevant learning questions are unknown in advance, or hyper-parameter tuning plays a central role, one solution is to release a differentially private synthetic data set that leads to similar conclusions as the original training data. In this work, we introduce an algorithm that enjoys fast rates for the utility loss for sparse Lipschitz queries. Furthermore, we show how to obtain a certificate for the utility loss for a large class of algorithms.} }
Endnote
%0 Conference Paper %T Certified private data release for sparse Lipschitz functions %A Konstantin Donhauser %A Johan Lokna %A Amartya Sanyal %A March Boedihardjo %A Robert Hönig %A Fanny Yang %B Proceedings of The 27th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2024 %E Sanjoy Dasgupta %E Stephan Mandt %E Yingzhen Li %F pmlr-v238-donhauser24a %I PMLR %P 1396--1404 %U https://proceedings.mlr.press/v238/donhauser24a.html %V 238 %X As machine learning has become more relevant for everyday applications, a natural requirement is the protection of the privacy of the training data. When the relevant learning questions are unknown in advance, or hyper-parameter tuning plays a central role, one solution is to release a differentially private synthetic data set that leads to similar conclusions as the original training data. In this work, we introduce an algorithm that enjoys fast rates for the utility loss for sparse Lipschitz queries. Furthermore, we show how to obtain a certificate for the utility loss for a large class of algorithms.
APA
Donhauser, K., Lokna, J., Sanyal, A., Boedihardjo, M., Hönig, R. & Yang, F.. (2024). Certified private data release for sparse Lipschitz functions. Proceedings of The 27th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 238:1396-1404 Available from https://proceedings.mlr.press/v238/donhauser24a.html.

Related Material