• Bokmål
  • English

Sitemap

Publication profile

Publication profile

Martin Jullum

Martin, Jullum
Name: Martin Jullum
Title: Seniorforsker / Senior Research Scientist
Phone: (+47) +47 22 85 26 08 Mob: +47 476 33 245
Email: Jullum [at] nr [dot] no
Scientific areas: Statistical analysis and methodology, Machine learning, Model selection
Add to contacts (vCard)
 Show publications

 

Academic article
2021
Jullum, Martin; Redelmeier, Annabelle Alice; Aas, Kjersti. Efficient and simple prediction explanations with groupShapley: A practical perspective. CEUR Workshop Proceedings (ISSN 1613-0073). 3014 2021. Fulltekst
Främling, Kary; Westberg, Marcus; Jullum, Martin; Madhikermi, Manik; Malhi, Avleen Kaur. Comparison of Contextual Importance and Utility with LIME and Shapley Values. Lecture Notes in Computer Science (LNCS) (ISSN 0302-9743). 12688 pp 39-54. doi: 10.1007/978-3-030-82017-6_3. 2021.
Aas, Kjersti; Nagler, Thomas; Jullum, Martin; Løland, Anders. Explaining predictive models using Shapley values and non-parametric vine copulas. Dependence Modeling (ISSN 2300-2298). 9(1) pp 62-81. doi: 10.1515/demo-2021-0103. 2021. Fulltekst
Aas, Kjersti; Jullum, Martin; Løland, Anders. Explaining individual predictions when features are dependent: More accurate approximations to Shapley values. Artificial Intelligence (ISSN 0004-3702). 298 doi: 10.1016/j.artint.2021.103502. 2021.
2020
Sellereite, Nikolai; Jullum, Martin. shapr: An R-package for explaining machine learning models with dependence-aware Shapley values. Journal of Open Source Software (JOSS) (ISSN 2475-9066). 5(46) doi: 10.21105/joss.02027. 2020. Arkiv
Jullum, Martin. Investigating mesh-based approximation methods for the normalization constant in the log Gaussian Cox process likelihood. Stat (ISSN 2049-1573). 9(1) doi: 10.1002/sta4.285. 2020.
Jullum, Martin; Thorarinsdottir, Thordis Linda; Bachl, Fabian E.. Estimating seal pup production in the Greenland Sea by using Bayesian hierarchical modelling. The Journal of the Royal Statistical Society, Series C (Applied Statistics) (ISSN 0035-9254). 69(2) doi: 10.1111/rssc.12397. 2020.
Jullum, Martin; Løland, Anders; Huseby, Ragnar Bang; Ånonsen, Geir; Lorentzen, Johannes P. Detecting money laundering transactions with machine learning. Journal of Money Laundering Control (ISSN 1368-5201). 23(1) pp 173-186. doi: 10.1108/JMLC-07-2019-0055. 2020. Fulltekst
Otneim, Håkon; Jullum, Martin; Tjøstheim, Dag Bjarne. Pairwise local Fisher and naive Bayes: Improving two standard discriminants. Journal of Econometrics (ISSN 0304-4076). 216(1) pp 284-304. doi: 10.1016/j.jeconom.2020.01.019. 2020. Arkiv
2018
Jullum, Martin; Hjort, Nils Lid. What price semiparametric Cox regression? Lifetime Data Analysis (ISSN 1380-7870). 25(3) pp 406-438. doi: 10.1007/s10985-018-9450-7. 2018. Fulltekst Arkiv
2017
Jullum, Martin; Hjort, Nils Lid. Parametric or nonparametric: The FIC approach. Statistica sinica (ISSN 1017-0405). 27(3) pp 951-981. doi: 10.5705/ss.202015.0364. 2017.
2016
Kolbjørnsen, Odd; Buland, Arild; Hauge, Ragnar; Røe, Per; Jullum, Martin; Metcalfe, Richard William; Skjæveland, Øyvind. Bayesian AVO inversion to rock properties using a local neighborhood in a spatial prior model. The Leading Edge (ISSN 1070-485X). 35(5) pp 431-436. doi: 10.1190/tle35050431.1. 2016.
Jullum, Martin; Kolbjørnsen, Odd. A Gaussian-based framework for local Bayesian inversion of geophysical data to rock properties. Geophysics (ISSN 0016-8033). 81(3) pp R75-R87. doi: 10.1190/geo2015-0314.1. 2016.
2015
Jullum, Martin; Kolbjørnsen, Odd. A Gaussian-based framework for local Bayesian inversion of geophysical data to rock properties. Geophysics (ISSN 0016-8033). 81(3) pp R75-R87. doi: 10.1190/GEO2015-0314.1. 2015.
Academic chapter/article/Conference paper
2020
Redelmeier, Annabelle Alice; Jullum, Martin; Aas, Kjersti. Explaining Predictive Models with Mixed Features Using Shapley Values and Conditional Inference Trees. In: Lecture Notes in Computer Science (LNCS). (ISBN 978-3-030-58805-2). pp 117-137. doi: 10.1007/978-3-030-57321-8_7. 2020. Arkiv
2015
Hermansen, Gudmund Horn; Hjort, Nils Lid; Jullum, Martin. Parametric or nonparametric: the FIC approach for stationary time series. In: Proceedings of the 60th World Statistics Congress of the International Statistical Institute, ISI2015. (ISBN 978-90-73592-35-3). pp 4827-4832. 2015. Fulltekst
Academic lecture
2022
Jullum, Martin. Prediction Explanation with Shapley values. Explainable AI Seminars @ Imperial; Online, 2/3/2022.
2021
Jullum, Martin; Redelmeier, Annabelle Alice; Aas, Kjersti. Efficient Shapley value explanations through feature groups. The 28th Nordic Conference in Mathematical Statistics; Tromsø, Norway/ Online, 6/21/2021 - 6/24/2021.
Jullum, Martin; Aas, Kjersti; Løland, Anders. Explaining individual predictions when features are dependent: More accurate approximations to Shapley values. 30th International Joint Conference on Artificial Intelligence; Online/Montreal, 8/19/2021 - 8/26/2021.
Jullum, Martin; Redelmeier, Annabelle Alice; Aas, Kjersti. Efficient and simple prediction explanations with groupShapley: A practical perspective. Italian Workshop on Explainable Artificial Intelligence 2021; Milano, Italy/ Online, 12/1/2021 - 12/3/2021.
2020
Jullum, Martin. How to open the black box – individual prediction explanation. Statistics seminar series at Department of Mathematical Sciences, NTNU; Trondheim, 3/9/2020.
2019
Jullum, Martin; Aas, Kjersti; Løland, Anders. Opening the black box -- individual prediction explanation. Big Insight Day 2020; Oslo, 11/14/2019.
Jullum, Martin; Aas, Kjersti; Løland, Anders. How to open the black box -- Individual prediction explanation. Det 20. norske statistikermøtet; Stavanger, 6/18/2019 - 6/20/2019.
2018
Jullum, Martin; Hjort, Nils Lid. Parametric or nonparametric, that’s the question. The FocuStat conference 2018, 5/22/2018 - 5/25/2018.
2017
Jullum, Martin; Thorarinsdottir, Thordis Linda; Bachl, Fabian. Estimating the seal pup abundance in the Greenland Sea with Bayesian hierarchical modeling. Det 17. norske statistikermøtet; Fredrikstad, 6/12/2017 - 6/15/2017.
Jullum, Martin. A focused model selection criterion for selecting among parametric and nonparametric models. Building Bridges at Bislett, 5/22/2017 - 5/24/2017.
Thorarinsdottir, Thordis Linda; Jullum, Martin; Guttorp, Peter. Bayesian modelling of cluster point process models. Spatial Statistics 2017; Lancaster, 7/4/2017 - 7/7/2017.
2016
Jullum, Martin; Thorarinsdottir, Thordis Linda; Bachl, Fabian. Estimating seal pup abundance with LGCP. Autumn Meeting on Latent Gaussian Models, 10/10/2016 - 10/11/2016.
Jullum, Martin. FIC with a nonparametric candidate – a new strategy for FIC construction. FICology; Oslo, 5/9/2016 - 5/11/2016.
2015
Jullum, Martin; Kolbjørnsen, Odd. An Approximate Bayesian Inversion Framework based on Local-gaussian Likelihoods. Petroleum Geostatistics; Biarritz, 9/7/2015 - 9/11/2015.
Jullum, Martin. An approximate Bayesian geophysical inversion framework based on local-Gaussian likelihoods. Oslo Graduate School in Biostatistics Workshop; Klækken, Hønefoss, 5/29/2015 - 5/30/2015.
Jullum, Martin. Parametric of Nonparametric: The FIC Approach for Time Series. 18th Norwegian Statistical Meeting; Solstrand, Bergen, 6/16/2015 - 6/18/2015. Omtale
2014
Jullum, Martin; Hjort, Nils Lid. Parametric or Nonparametric: The Focused Information Criterion Approach. 2014 Joint Statistical Meetings; Boston, 8/2/2014 - 8/7/2014.
2013
Jullum, Martin. Parametric or Nonparametric: The Focused Information Criterion Approach (+ Approximate Bayesian Inference). SFI-lunsj; Norsk Regnesentral, Oslo, 10/20/2013.
Jullum, Martin; Hjort, Nils Lid. Parametric or Nonparametric: The FIC Approach. 29-th European Meeting of Statisticians; Budapest, 7/20/2013 - 7/25/2103 1:00:00 AM.
Jullum, Martin; Hjort, Nils Lid. Parametric or Nonparametric: The FIC Approach. 17th Norwegian Statistical meeting; Halden, 6/11/2013 - 6/13/2013.
Abstract
2015
Jullum, Martin; Kolbjørnsen, Odd. An Approximate Bayesian Inversion Framework based on Local-Gaussian Likelihoods. EarthDoc. doi: 10.3997/2214-4609.201413634. 2015. Omtale
Lecture
2019
Jullum, Martin; Bolstad, Lars Erik. Mindre rutinearbeid med maskinlæring -- Automatisk deteksjon av hvitvasking. Make Data Smart Again; Oslo, 5/9/2019.
2018
Jullum, Martin. XGBoost - efficient tree boosting. Big Insight lunch seminar, 1/31/2018.
Løland, Anders; Jullum, Martin; Huseby, Ragnar Bang. Detecting money laundering transactions – two stories. DNB Data Summit 2018; Oslo, 11/30/2018.
2016
Jullum, Martin. New focused approaches to topics within model selection and approximate Bayesian inversion. Disputas, 4/1/2016.
Jullum, Martin. Empirical likelihood. Trial lecture, PhD, 4/1/2016.
2013
Jullum, Martin. Approximate Bayesian Inference for Geophysical Inverse Problems. Oslo Graduate School in Biostatistics Workshop; Hønefoss, 5/24/2013 - 5/25/2013.
Poster
2021
Aas, Kjersti; Jullum, Martin; Løland, Anders. Explaining individual predictions when features are dependent: More accurate approximations to Shapley values. The 30th International Joint Conference on Artificial Intelligence (IJCAI-21); Montreal (virtuelt), 8/19/2021 - 8/26/2021.
Jullum, Martin. groupSHAP: Efficient Shapley value explanation through feature groups. Geilo Winter School; Online, 1/25/2021 - 3/29/2021.
Doctoral dissertation
2016
Jullum, Martin; Kolbjørnsen, Odd. New focused approaches to topics within model selection and approximate Bayesian inversion. Faculty of Mathematics and Natural Sciences, University of Oslo. pp 185. 2016.
Masters thesis
2012
Jullum, Martin. Focused information criteria for selecting among parametric and nonparametric models.. 2012. Omtale
Report
2021
Jullum, Martin; Redelmeier, Annabelle Alice; Aas, Kjersti. groupShapley: Efficient prediction explanation with Shapley values for feature groups. Norsk Regnesentral. NR-notat SAMBA/20/21. 2021.
Grotmol, Øyvind; Scheuerer, Michael; Aas, Kjersti; Jullum, Martin. Whitepaper on Exabel’s Factor Model. EXABEL. pp 7. 2021.
Grotmol, Øyvind; Jullum, Martin; Aas, Kjersti; Scheuerer, Michael. White paper on performance evaluation of volatility estimation methods for Exabel. EXABEL. pp 12. 2021.
2019
Redelmeier, Annabelle Alice; Aas, Kjersti; Jullum, Martin; Løland, Anders. Shapley explanations using conditional inference trees. Norsk Regnesentral. NR-notat SAMBA/18/19. pp 33. 2019.
2018
Jullum, Martin; Løland, Anders; Huseby, Ragnar Bang; Ånonsen, Geir; Lorentzen, Johannes P. Detecting money laundering transactions -- which transactions should we learn from? Norsk Regnesentral. NR-notat SAMBA/06/18. pp 22. 2018.
Jullum, Martin; Thorarinsdottir, Thordis Linda; Bachl, Fabian. Estimating seal pup production in the Greenland Sea using Bayesian hierarchical modeling. Norsk Regnesentral. NR-notat SAMBA/04/18. pp 25. 2018. Fulltekst
2017
Holden, Lars; Jullum, Martin; Sandve, Geir Kjetil. Statistical modeling of repertoire overlap in entire sampling spaces. Norsk Regnesentral. NR-notat SAMBA/13/2017. pp 15. 2017. Fulltekst
Aas, Kjersti; Jullum, Martin; Neef, Linda Reiersølmoen. Maskinlæring for vurdering av forsikringsrisiko. Norsk Regnesentral. NR-notat SAMBA/14/2017. pp 81. 2017.
2011
Jullum, Martin. Hypotesetesting av strekklengde for Seigmenn. Norsk Regnesentral. NR-notat SAMBA/25/11. pp 28. 2011.
Jullum, Martin. Vindprognoser og strømpriser. Norsk Regnesentral. NR-notat SAMBA/26/11. pp 21. 2011.
Popular scientific article
2011
Storvik, Bård; Jullum, Martin. Strekker Laban seg litt lengre? Forskning.no (ISSN 1891-635X). 9/29/2011. Fulltekst
Programme participation
2015
Jullum, Martin; Banos, David Ruiz. Hvis man sjekker en billion kvinner, vil man finne fem slike par. 2015. Aftenposten TV [TV] 10/22/2015. Fulltekst
Website (informational material)
2015
Hjort, Nils Lid; Jullum, Martin. To liv: kvinnene i Lillestrøm som ble født på samme dag og døde på samme dag (FocuStat Blog Post). 2015. Fulltekst
Hjort, Nils Lid; Jullum, Martin. To liv: kvinnene i Lillestrøm som ble født på samme dag og døde på samme dag. 2015. Data
Postal address:
Norsk Regnesentral/
Norwegian Computing Center
P.O. Box 114 Blindern
NO-0314 Oslo
Norway
Visit address:
Norsk Regnesentral
Gaustadalleen 23a
Kristen Nygaards hus
NO-0373 Oslo.
Phone:
(+47) 22 85 25 00
Address How to get to NR
Social media Share on social media
Privacy policy Privacy policy
Postal address: Norsk Regnesentral/Norwegian Computing Center, P.O. Box 114 Blindern, NO-0314 Oslo, Norway
Visit address: Norsk Regnesentral, Gaustadalleen 23a, Kristen Nygaards hus, NO-0373 Oslo.
Phone: (+47) 22 85 25 00
AddressHow to get to NR