Lars Henry Berge Olsen

Doctoral Research Fellow - Statistics and Data Science
Image of Lars Henry Berge Olsen
Norwegian version of this page
Email lholsen@math.uio.no
Room 806
Username
Visiting address Moltke Moes vei 35 Niels Henrik Abels hus 0851 Oslo
Postal address Postboks 1053 Blindern 0316 Oslo
Other affiliations Faculty of Mathematics and Natural Sciences (Student)

Academic interests

I am working on methods for using the Shapley value apparatus from cooperative game theory as a model-agnostic explanation method for interpreting machine learning models / black-box models.

Background

Master's degree in Data Science from UiO (2020): Likelihood-Based Boosting: Approximate Confidence Bands and Intervals for Generalized Additive Models.

Bachelor's degree in Applied Mathematics from UiO (2018).

Partners

My supervisors are Ingrid Glad, Kjersti Aas, and Martin Jullum.

 

Tags: Statistics, data science, Artificial intelligence

Publications

  • Olsen, Lars Henry Berge; Glad, Ingrid Kristine; Jullum, Martin & Aas, Kjersti (2022). Using Shapley Values and Variational Autoencoders to Explain Predictive Models with Dependent Mixed Features. Journal of machine learning research. ISSN 1532-4435. 23(213), p. 1–51. Full text in Research Archive

View all works in Cristin

Published Sep. 18, 2020 1:46 PM - Last modified Oct. 9, 2020 9:13 AM

Research groups