Friedrich Dörmann

According to our database, Friedrich Dörmann authored at least 2 papers in 2021.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2021

Not All Noise is Accounted Equally: How Differentially Private Learning Benefits from Large Sampling Rates.

Friedrich Dörmann, Osvald Frisk, Lars Nørvang Andersen, Christian Fischer Pedersen

Proceedings of the 2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP), 2021

Super-convergence and Differential Privacy: Training faster with better privacy guarantees.

Osvald Frisk, Friedrich Dörmann, Christian Marius Lillelund, Christian Fischer Pedersen

Proceedings of the 55th Annual Conference on Information Sciences and Systems, 2021