Goto

Collaborating Authors

 Country


OnPrivacyandPersonalizationin Cross-SiloFederatedLearning

Neural Information Processing Systems

While theapplication ofdifferential privacy(DP) hasbeen well-studied incrossdevice federated learning (FL), there is a lack of work considering DP and its implications for cross-silo FL, a setting characterized by a limited number of clients each containing many data subjects.



Batches

Neural Information Processing Systems

In this paper, we find an appealing way to synthesize [JO19] and [CLM19] to give the best of both worlds: an algorithm which runs in polynomial time and can exploit structure in the underlying distribution to achieve sublinear sample complexity.





271ec4d1a9ff5e6b81a6e21d38b1ba96-Paper-Conference.pdf

Neural Information Processing Systems

Motivated by recent applications requiring differential privacy over adaptive streams, we investigate optimal instantiations of the matrix mechanism [1] in this setting. Weprovefundamental theoretical results ontheapplicability ofmatrix factorizations to adaptive streams, and provide a parameter-free fixed-point algorithm for computing optimal factorizations.