3 citations · 4 across the 3 of their papers we have counts for
7 papers
A Comparison of the Delta Method and the Bootstrap in Deep Learning Classification
Geir K. Nilsen, Antonella Z. Munthe-Kaas, Hans J. Skaug +1
We validate the recently introduced deep learning classification adapted Delta method by a comparison with the classical Bootstrap. We show that there is a strong linear relationsh…
An information criterion for automatic gradient tree boosting
Berent Ånund Strømnes Lunde, Tore Selland Kleppe, Hans Julius Skaug
An information theoretic approach to learning the complexity of classification and regression trees and the number of trees in gradient tree boosting is proposed. The optimism (tes…
Heritability curves: a local measure of heritability
Geir D. Berentsen, Francesca Azzolini, Hans J. Skaug +2
This paper introduces a new measure of heritability which relaxes the classical assumption that the degree of heritability of a continuous trait can be summarized by a single numbe…
Epistemic Uncertainty Quantification in Deep Learning Classification by the Delta Method
Geir K. Nilsen, Antonella Z. Munthe-Kaas, Hans J. Skaug +1
The Delta method is a classical procedure for quantifying epistemic uncertainty in statistical models, but its direct application to deep neural networks is prevented by the large…
Efficient Computation of Hessian Matrices in TensorFlow
Geir K. Nilsen, Antonella Z. Munthe-Kaas, Hans J. Skaug +1
The Hessian matrix has a number of important applications in a variety of different fields, such as optimzation, image processing and statistics. In this paper we focus on the prac…
Saddlepoint-adjusted inversion of characteristic functions
Berent Å. S. Lunde, Tore S. Kleppe, Hans J. Skaug
For certain types of statistical models, the characteristic function (Fourier transform) is available in closed form, whereas the probability density function has an intractable fo…