Logo: to the web site of Uppsala University

uu.sePublications from Uppsala University
Change search
Link to record
Permanent link

Direct link
Publications (2 of 2) Show all publications
Ek, S., Zachariah, D., Johansson, F. D. & Stoica, P. (2023). Off-Policy Evaluation with Out-of-Sample Guarantees. Transactions on Machine Learning Research
Open this publication in new window or tab >>Off-Policy Evaluation with Out-of-Sample Guarantees
2023 (English)In: Transactions on Machine Learning Research, E-ISSN 2835-8856Article in journal (Refereed) Published
National Category
Probability Theory and Statistics
Identifiers
urn:nbn:se:uu:diva-519244 (URN)
Available from: 2024-01-04 Created: 2024-01-04 Last updated: 2024-01-09Bibliographically approved
Ek, S., Zachariah, D. & Stoica, P. (2022). Learning Pareto-Efficient Decisions with Confidence. In: Camps-Valls, G Ruiz, FJR Valera, I (Ed.), International Conference on Artificial Intelligence and Statistics: . Paper presented at International Conference on Artificial Intelligence and Statistics, MAR 28-30, 2022, ELECTR NETWORK (pp. 9969-9981). JMLR-JOURNAL MACHINE LEARNING RESEARCH, 151
Open this publication in new window or tab >>Learning Pareto-Efficient Decisions with Confidence
2022 (English)In: International Conference on Artificial Intelligence and Statistics / [ed] Camps-Valls, G Ruiz, FJR Valera, I, JMLR-JOURNAL MACHINE LEARNING RESEARCH , 2022, Vol. 151, p. 9969-9981Conference paper, Published paper (Refereed)
Abstract [en]

The paper considers the problem of multi-objective decision support when outcomes are uncertain. We extend the concept of Pareto-efficient decisions to take into account the uncertainty of decision outcomes across varying contexts. This enables quantifying trade-offs between decisions in terms of tail outcomes that are relevant in safety-critical applications. We propose a method for learning efficient decisions with statistical confidence, building on results from the conformal prediction literature. The method adapts to weak or nonexistent context covariate overlap and its statistical guarantees are evaluated using both synthetic and real data.

Place, publisher, year, edition, pages
JMLR-JOURNAL MACHINE LEARNING RESEARCH, 2022
Series
Proceedings of Machine Learning Research, ISSN 2640-3498
National Category
Probability Theory and Statistics
Identifiers
urn:nbn:se:uu:diva-487888 (URN)000841852304022 ()
Conference
International Conference on Artificial Intelligence and Statistics, MAR 28-30, 2022, ELECTR NETWORK
Funder
Knut and Alice Wallenberg FoundationSwedish Research Council, 2018-05040Swedish Research Council, 2021-05022
Available from: 2022-11-14 Created: 2022-11-14 Last updated: 2023-04-03Bibliographically approved
Organisations
Identifiers
ORCID iD: ORCID iD iconorcid.org/0000-0003-1303-2901

Search in DiVA

Show all publications