We present SEALion: an extensible framework for privacy-preserving machi...
Differentially private learning on real-world data poses challenges for
...
Optimal Transport offers an alternative to maximum likelihood for learni...
Consider two data providers, each maintaining records of different featu...
We present a theoretically grounded approach to train deep neural networ...
It is usual to consider data protection and learnability as conflicting
...
We prove that the empirical risk of most well-known loss functions facto...