2 papers
cs.LG2021
Not all noise is accounted equally: How differentially private learning benefits from large sampling rates
Friedrich Dörmann, Osvald Frisk, Lars Nørvang Andersen +1
Learning often involves sensitive data and as such, privacy preserving extensions to Stochastic Gradient Descent (SGD) and other machine learning algorithms have been developed usi…
cs.LG2021
Even your Teacher Needs Guidance: Ground-Truth Targets Dampen Regularization Imposed by Self-Distillation
Kenneth Borup, Lars N. Andersen
Knowledge distillation is classically a procedure where a neural network is trained on the output of another network along with the original targets in order to transfer knowledge…