212 citations · 505 across the 43 of their papers we have counts for
Showing 2024Show all
2 papers · 1 filter
stat.ML2024
Subsampling is not Magic: Why Large Batch Sizes Work for Differentially Private Stochastic Optimisation
Ossi Räisä, Joonas Jälkö, Antti Honkela
We study how the batch size affects the total gradient variance in differentially private stochastic gradient descent (DP-SGD), seeking a theoretical explanation for the usefulness…
cs.LG2024
A Bias-Variance Decomposition for Ensembles over Multiple Synthetic Datasets
Ossi Räisä, Antti Honkela
Recent studies have highlighted the benefits of generating multiple synthetic datasets for supervised learning, from increased accuracy to more effective model selection and uncert…