Adam Johansen is a Professor of Statistics; his research focuses upon methodological and theoretical aspects of simulation-based algorithms.
He led the Robust, Scalable Sequential Monte Carlo with Application To Urban Air Quality project and was an investigator within The CoSinES Project.
He is an investigator within the OCEAN Project.
He was a co-director of APTS from 2012–2023.

Teaching

Some generic teaching information - - applicable to my personal tutees, MSc students and those attending my lectures is available from my teaching page.

Research

Current interests include Monte Carlo methodology, particularly sequential methods together with Bayesian statistics and decision theory more generally.

Information about former students and postdoctoral researchers.

Prospective Ph.D. students should feel free to email me to discuss possible research directions and might find the theses of some of my former students (available by following the above link) useful indicators of the types of project in which I am typically involved.

Current Research Group

Postdoctoral Researchers

• Adrien Corenflos (part of the OCEAN Project)
• Filippo Pagani (part of the OCEAN Project)

PhD Students

• Rocco Caprio (co-supervisor Andi Wang)
• Shu Huang (co-supervisors Richard Everitt and Massimiliano Tamborrino)
• Janique Krasnowska (co-supervisor Paul Jenkins)
• Usman Ladan (co-supervisors Emma Horton and Andreas Kyprianou)
• Jen Ning Lim
• Liwen Xue

Publications

(Pre)Publications to date are listed here. Selected recent additions are listed below.

• J. N. Lim, J. Kuntz, S. Power, and A. M. Johansen. Momentum particle maximum likelihood. In Proceedings of 41st International Conference on Machine Learning (ICML), Vienna, Austria, July 2024. In press. [arxiv]
• J. Kuntz, F. R. Crucinio, and A. M. Johansen. Divide-and-conquer Sequential Monte Carlo: Properties and limit theorems. Annals of Applied Probability, 34(1B):1469-1523. 2024. [journal|arxiv]
• R. Chan, M. Pollock, A. M. Johansen, and G. O. Roberts. Divide-and-conquer Monte Carlo Fusion. Journal of Machine Learning Research, 174(193):1-82, 2023. [journal|arxiv]
• F. R. Crucinio, A. Doucet, and A. M. Johansen. A particle method for solving Fredholm integral equations of the first kind. Journal of the American Statistical Association, 118:542, 937-947, 2023. [journal|arxiv]
• J. Kuntz and J. N. Lim A. M. Johansen. Particle algorithms for maximum likelihood training of latent variable models. In Proceedings of The 26th International Conference on Artificial Intelligence and Statistics, PMLR 206:5134-5180, 2023. (oral presentation). [proceedings|arxiv]
• J. Hodgson, A. M. Johansen, and M. Pollock. Unbiased simulation of rare events in continuous time. Methodology and Computing in Applied Probability, 24:2123-2148, 2022. [journal|arxiv]
• L. J. Rendell, A. M. Johansen, A. Lee and N. Whiteley. Global consensus Monte Carlo. Journal of Computational and Graphical Statistics 30(2):249–259, 2021. [journal|arxiv]
• M. Pollock, P. Fearnhead, A. M. Johansen and G. O. Roberts. Quasi-stationary Monte Carlo methods and the ScaLE algorithm.Journal of the Royal Statistical Society Series B (Statistical Methodology) 82(5):1167–1221, 2020. [journal|arxiv]
• A. Finke, A. Doucet, and A. M. Johansen. Limit theorems for sequential MCMC methods. Advances in Applied Probability 52(2):377-403, 2020 [journal|arxiv]
• J. Koskela, P. Jenkins, A. M. Johansen, and D. Spanò. Asymptotic genealogies of interacting particle systems with an application to sequential Monte Carlo. Annals of Statistics 48(1):560–583, 2020 as corrected in Erratum: Asymptotic genealogies of interacting particle systems with an application to sequential Monte Carlo. Annals of Statistics, 50(4):2467 – 2468, 2022. [journal|arxiv]

Editorial and Committee Responsibilities

I am currently:

• Chair of the RSS Statistical Computing and Machine Learning Section
• Associate Editor for Journal of the Royal Statistical Society: Series B (Statistical Methodology)

Previous roles include:

• Comissioning Editor for the Newsletter of the London Mathematical Society (2018–2023)

Software

• SMCTC: A Sequential Monte Carlo Template Class (C++)
• RcppSMC: An Rcpp library which has evolved from the above (currently version 0.2.6) ; the development version of RcppSMC lives on github and a google-groups-based discussion list also exists.

 

Adam M. Johansen

MSB 2.18

024761- 50919

a dot m dot johansen at warwick.ac.uk