Research

Keywords: Bayesian statistics, computational statistics, Monte-Carlo methods, Markov random fields, model selection, approximate Bayesian computation (ABC), composite likelihood.

ORCID iD icon https://orcid.org/0000-0002-7813-0185

Publications

  1. Stoehr, J. and Robin, S. (2024) Composite likelihood inference for the Poisson log-normal model.

    arXiv version.

  2. Robert, C. P. and Stoehr, J. (2024) Simulating signed mixtures.

    arXiv version.

  3. Clarté, G., Robert, C. P., Ryder, R and Stoehr, J. (2021) Component-wise approximate Bayesian computation via Gibbs-like steps. Biometrika. Vol. 108, issue 3, pp. 591-607(doi:10.1093/biomet/asaa090).

    Journal & arXiv versions.

  4. Wu, C., Stoehr, J., and Robert, C. P. (2019) Faster Hamiltonian Monte Carlo by Learning Leapfrog Scale.

    arXiv version.

  5. Stoehr, J., Benson, A. and Friel, N. (2018) Noisy Hamiltonian Monte Carlo for doubly-intractable distributions. Journal of Computational and Graphical Statistics. Vol. 28, No. 1, pp. 220-232 (doi: 10.1080/10618600.2018.1506346).

    Journal & arXiv versions.

  6. Stoehr, J., (2017) A review on statistical inference methods for discrete Markov random fields.

    arXiv version.

  7. Stoehr, J., Marin, J.-M. and P. Pudlo (2016) Hidden Gibbs random fields model selection using Block Likelihood Information Criterion. Stat. Vol. 5, pp. 158-172 (doi: 10.1002/sta4.112).

    Journal & arXiv versions.

  8. Stoehr, J. and Friel, N. (2015) Calibration of conditional composite likelihood for Bayesian inference on Gibbs random fields. Journal of Machine Learning Research: Workshop and Conference Proceedings. Volume 38: Proceedings of the Eighteenth International Conference on Artificial Intelligence and Statistics, pp. 921–929.

    Journal & arXiv versions.

  9. Stoehr, J., Pudlo, P. and Cucala, L. (2015) Adaptive ABC model choice and geometric summary statistics for hidden Gibbs random fields. Statistics and Computing. Vol. 25, issue 1, pp. 129-141 (doi: 10.1007/s11222-014-9514-9).

    Journal & arXiv

Invited talks

  1. ENBIS 2023, invited in the SFdS session, September 11, 2023, Valencia (Spain)
  2. Journées MAS, August 26 2021, invited in the session "Développements récents en Bayésien computationnel" (Online. Organised by Nicolas Chopin)
  3. 2021 ISBA World Meeting, June 28, 2021, invited in the session "Approximate Bayesian inference" (Online. Organised by Christian P. Robert).
  4. MCM 2019, UNSW, July 8-12, 2019, invited in the session "Approximate Bayesian Computation" (Organised by Christian P. Robert), Sydney (Australia).
  5. CRiSM Day on Bayesian Intelligence, University of Warwick, March 20, 2019, Warwick (UK).
  6. Practical at Masterclass in Bayesian Statistics, CIRM, October 22, 2018, Marseille (France).
  7. ABCruise, May 16-18, 2016, Helsinki-Stockholm (Finland-Sweden).
  8. CMStatistics 2015, December 13, 2015, London (UK).
  9. Algorithmic Issues for Inference in Graphical Models (AIGM) workshop, June 30, 2015, Grenoble (France)

Seminars

  1. Séminaire de l'équipe de Géostatistique des Mines de Paris - PSL, May 16, 2024, Fontainebleau (France)
  2. Séminaire Statistique de l'IMAG, April 22, 2024, Montpellier (France)
  3. Séminaire Statistique Aix Marseille Université, November 20, 2023, Marseille (France)
  4. Séminaire INRAE MIA Paris-Saclay, September 21, 2023, Paris (France)
  5. Séminaire Parisien de Statistique, IHP, October 17, 2022, Paris (France).
  6. Séminaire Statistique des sommets de Rochebrune, March 21-25, 2022, Rochebrune (France)
  7. Séminaire INRAE MIAT, September 20, 2019, Toulouse (France).
  8. Séminaire Statistique, université Paris-Saclay, January 17, 2019, Paris (France).
  9. Séminaire, université Grenoble Alpes (LJK), January 10, 2019, Grenoble (France).
  10. Séminaire, AgroParisTech, October 15, 2018, Paris (France).
  11. Séminaire, université de Montpellier, January 22, 2018, Montpellier (France).
  12. Séminaire Parisien de Statistique, IHP, November 13, 2017, Paris (France).
  13. Séminaire, université Paris-Saclay, March 23, 2017, Paris (France).
  14. Séminaire, AgroParisTech, January 26, 2017, Paris (France).
  15. Séminaire, Ecole Polytechnique, January 25, 2017, Paris (France).
  16. Séminaire, université Aix-Marseille, November 21, 2016, Marseille (France).
  17. Séminaire, Insight Centre for Data Analytics, May 11, 2016, Dublin (Ireland).
  18. Séminaire, INRIA MISTIS, January 22nd 2016, Grenoble (France).
  19. Séminaire, INRIA MODAL, September 15, 2015, Lille (France).
  20. Séminaire, INRAE, December 18, 2014, Avignon (France)
  21. Séminaire, université de Montpellier, November 3, 2014, Montpellier (France)

Reviewed conferences

  1. 54ème Journées de Statistique de la SFdS, July 6, 2023, Paris (France): A Monte Carlo EM for the Poisson log-normal model.
  2. 2018 ISBA World Meeting, June 28, 2018, Edimburgh (Scotland): Pre-Stored Likelihood-Free Inference.
  3. 50ème Journées de Statistique de la SFdS, May 29, 2018, Paris (France): Pre-Stored Likelihood-Free Inference.
  4. 47ème Journées de Statistique de la SFDS (French Statistics Society conference), June 5, 2015, Lille (France): Critères de choix de modèle pour champs de Gibbs cachés
  5. 46ème Journées de Statistique de la SFdS, June 3, 2014, Rennes (France): Statistiques résumées géométriques pour le choix de modèle ABC entre des champs de Gibbs cachés.

Posters

  1. Poster, AISTATS 2015, May 10, 2015, San Diego (USA): Calibration of conditional composite likelihood for Bayesian inference on Gibbs random fields.
  2. Poster, MCMSki IV, January 7, 2014, Chamonix (France): ABC model choice between hidden Gibbs random fields based on geometric summary statistics
  3. Poster, ABC in Rome, May 30, 2013, Roma (Italy): Model choice for hidden Gibbs random fields using Approximate Bayesian Computation.