23 citations · 87 across the 23 of their papers we have counts for
Showing stat.MLShow all
3 papers · 1 filter
stat.ML2020★ 3 cited
Tight Differential Privacy for Discrete-Valued Mechanisms and for the Subsampled Gaussian Mechanism Using FFT
Antti Koskela, Joonas Jälkö, Lukas Prediger +1
We propose a numerical accountant for evaluating the tight -privacy loss for algorithms with discrete one dimensional output. The method is based on the privacy lo…
stat.ML2019★ 11 cited
Computing Tight Differential Privacy Guarantees Using FFT
Antti Koskela, Joonas Jälkö, Antti Honkela
Differentially private (DP) machine learning has recently become popular. The privacy loss of DP algorithms is commonly reported using -DP. In this paper, we propo…
stat.ML2018★ 10 cited
Learning Rate Adaptation for Federated and Differentially Private Learning
Antti Koskela, Antti Honkela
We propose an algorithm for the adaptation of the learning rate for stochastic gradient descent (SGD) that avoids the need for validation set use. The idea for the adaptiveness com…