Passer à la navigation principale Passer à la recherche Passer au contenu principal

Utility/Privacy Trade-off through the lens of Optimal Transport

  • ENS Paris-Saclay

Résultats de recherche: Contribution à un journal › Article de conférence › Revue par des pairs

7 Citations (Scopus)

Résumé

Strategic information is valuable either by remaining private (for instance if it is sensitive) or, on the other hand, by being used publicly to increase some utility. These two objectives are antagonistic and leaking this information might be more rewarding than concealing it. Unlike classical solutions that focus on the first point, we consider instead agents that optimize a natural trade-off between both objectives. We formalize this as an optimization problem where the objective mapping is regularized by the amount of information revealed to the adversary (measured as a divergence between the prior and posterior on the private knowledge). Quite surprisingly, when combined with the entropic regularization, the Sinkhorn loss naturally emerges in the optimization objective, making it efficiently solvable. We apply these techniques to preserve some privacy in online repeated auctions.

langue originaleAnglais
Pages (de - à)591-601
Nombre de pages11
journalProceedings of Machine Learning Research
Volume108
étatPublié - 1 janv. 2020
Evénement23rd International Conference on Artificial Intelligence and Statistics, AISTATS 2020 - Virtual, Online
Durée: 26 août 2020 → 28 août 2020

Empreinte digitale

Examiner les sujets de recherche de « Utility/Privacy Trade-off through the lens of Optimal Transport ». Ensemble, ils forment une empreinte digitale unique.

Contient cette citation