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
(2024).
A comparative study of methods for estimating model-agnostic Shapley value explanations.
Data mining and knowledge discovery.
ISSN 1384-5810.
doi:
10.1007/s10618-024-01016-z.
Full text in Research Archive
Show summary
Shapley values originated in cooperative game theory but are extensively used today as a model-agnostic explanation framework to explain predictions made by complex machine learning models in the industry and academia. There are several algorithmic approaches for computing different versions of Shapley value explanations. Here, we consider Shapley values incorporating feature dependencies, referred to as conditional Shapley values, for predictive models fitted to tabular data. Estimating precise conditional Shapley values is difficult as they require the estimation of non-trivial conditional expectations. In this article, we develop new methods, extend earlier proposed approaches, and systematize the new refined and existing methods into different method classes for comparison and evaluation. The method classes use either Monte Carlo integration or regression to model the conditional expectations. We conduct extensive simulation studies to evaluate how precisely the different method classes estimate the conditional expectations, and thereby the conditional Shapley values, for different setups. We also apply the methods to several real-world data experiments and provide recommendations for when to use the different method classes and approaches. Roughly speaking, we recommend using parametric methods when we can specify the data distribution almost correctly, as they generally produce the most accurate Shapley value explanations. When the distribution is unknown, both generative methods and regression models with a similar form as the underlying predictive model are good and stable options. Regression-based methods are often slow to train but quickly produce the Shapley value explanations once trained. The vice versa is true for Monte Carlo-based methods, making the different methods appropriate in different practical situations.
-
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
-
Løland, Anders & Olsen, Lars Henry Berge
(2024).
Fra BigInsight til Alan Turing-instituttet: En forklaring av forklaringer.
[Internet].
Sannsynligvis VIKTIG (podkast).
Show summary
Lars Henry Berge Olsen er til vanlig PhD-student ved BigInsight og Universitetet i Oslo, og akkurat nå er han ved Alan Turing-instituttet i London. Vi snakker om hva Alan Turing-instituttet er og om Lars' egen forskning på forklarbar kunstig intelligens, som kan ligne litt på en diskusjon om hvordan en bør dele taxi-regninga.
Med Anders Løland i studio, produsent er Elin Ruhlin Gjuvsland.
En podkastserie av Norsk Regnesentral.
View all works in Cristin
Published
Sep. 18, 2020 1:46 PM
- Last modified
May 25, 2023 1:44 PM