978 citations
- University of CopenhagenDK77 papers
- Technical University of DenmarkDK18 papers
- Institute for Scientific InterchangeIT17 papers
- Complexity Science HubAT16 papers
- Institut national de recherche en sciences et technologies du numériqueFR13 papers
- University College CopenhagenDK12 papers
- University of OxfordGB12 papers
- Aarhus UniversityDK11 papers
- Aalborg UniversityDK10 papers
- Chalmers University of TechnologySE10 papers
- ETH ZurichCH9 papers
- Google (United States)US9 papers
Showing 2019 · cs.LGShow all
2 papers · 2 filters
cs.LG2019★ 2 cited
On approximating dropout noise injection
Natalie Schluter
This paper examines the assumptions of the derived equivalence between dropout noise injection and regularisation for logistic regression with negative log loss. We show that…
cs.LG2019★ 65 cited
Scalable and Differentially Private Distributed Aggregation in the Shuffled Model
Badih Ghazi, Rasmus Pagh, Ameya Velingker
Federated learning promises to make machine learning feasible on distributed, private datasets by implementing gradient descent using secure aggregation methods. The idea is to com…