Open Problem: Do you pay for Privacy in Online learning?

Amartya Sanyal, Giorgia Ramponi
Proceedings of Thirty Fifth Conference on Learning Theory, PMLR 178:5633-5637, 2022.

Abstract

Online learning, in the mistake bound model, is one of the most fundamental concepts in learning theory and differential privacy is, perhaps, the most widely used statistical concept of privacy in the machine learning community. Thus, defining problems which are online differentially privately learnable is of great interest in learning theory. In this paper, we pose the question on if the two problems are equivalent from a learning perspective, i.e., is privacy for free in the online learning framework?

Cite this Paper

BibTeX
@InProceedings{pmlr-v178-open-problem-sanyal22a, title = {Open Problem: Do you pay for Privacy in Online learning?}, author = {Sanyal, Amartya and Ramponi, Giorgia}, booktitle = {Proceedings of Thirty Fifth Conference on Learning Theory}, pages = {5633--5637}, year = {2022}, editor = {Loh, Po-Ling and Raginsky, Maxim}, volume = {178}, series = {Proceedings of Machine Learning Research}, month = {02--05 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v178/open-problem-sanyal22a/open-problem-sanyal22a.pdf}, url = {https://proceedings.mlr.press/v178/open-problem-sanyal22a.html}, abstract = {Online learning, in the mistake bound model, is one of the most fundamental concepts in learning theory and differential privacy is, perhaps, the most widely used statistical concept of privacy in the machine learning community. Thus, defining problems which are online differentially privately learnable is of great interest in learning theory. In this paper, we pose the question on if the two problems are equivalent from a learning perspective, i.e., is privacy for free in the online learning framework?} }
Endnote
%0 Conference Paper %T Open Problem: Do you pay for Privacy in Online learning? %A Amartya Sanyal %A Giorgia Ramponi %B Proceedings of Thirty Fifth Conference on Learning Theory %C Proceedings of Machine Learning Research %D 2022 %E Po-Ling Loh %E Maxim Raginsky %F pmlr-v178-open-problem-sanyal22a %I PMLR %P 5633--5637 %U https://proceedings.mlr.press/v178/open-problem-sanyal22a.html %V 178 %X Online learning, in the mistake bound model, is one of the most fundamental concepts in learning theory and differential privacy is, perhaps, the most widely used statistical concept of privacy in the machine learning community. Thus, defining problems which are online differentially privately learnable is of great interest in learning theory. In this paper, we pose the question on if the two problems are equivalent from a learning perspective, i.e., is privacy for free in the online learning framework?
APA
Sanyal, A. & Ramponi, G.. (2022). Open Problem: Do you pay for Privacy in Online learning?. Proceedings of Thirty Fifth Conference on Learning Theory, in Proceedings of Machine Learning Research 178:5633-5637 Available from https://proceedings.mlr.press/v178/open-problem-sanyal22a.html.

Related Material