University of Cambridge > Talks.cam > Isaac Newton Institute Seminar Series > Bayesian inference of a non-local proliferation model

Bayesian inference of a non-local proliferation model

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact nobody.

MMVW03 - Measures and Representations of Interactions

Joint work with Jakub Skrzeczkowski, Błażej Miasojedow and Piotr Gwiazda. We present a new proliferation model of cells living within a colony, that is a non-local equation with a discontinuous interaction kernel. We discuss the range of applicability of the model, select suitable data and apply the Bayesian method to perform parameter estimation. We discuss proof of the problem’s well-posedness and investigate the convergence of the EBT algorithm applied to solve the equation. The main difficulty lies in the kernel’s low regularity, which is not Lipschitz continuous, thus preventing the application of standard arguments. Therefore, we use the radial symmetry of the problem instead and transform it using spherical coordinates. The resulting equation has a Lipschitz kernel with only one singularity at zero. We introduce a new weighted flat norm and prove that the particle method converges in this norm. We prove the problem’s well-posedness and investigate the convergence of the EBT algorithm applied to solve the equation. Finally, we prove the stability of posterior distributions in the total variation norm which exploits the theory of spaces of measures equipped with the weighted flat norm. References1 Szymańska, Z., Skrzeczkowski, J., Miasojedow, B., Gwiazda, P. “Bayesian inference of a non-local proliferation model”, R. Soc. Open Sci. 8(11), 211279, 2021;[2] Gwiazda, P., Miasojedow, B., Skrzeczkowski, J., Szymańska, Z., “Convergence of the EBT method for a non-local model of cell proliferation with discontinuous interaction kernel”, IMA J . Numer. Anal. 43(1), 590-626, 2023;

This talk is part of the Isaac Newton Institute Seminar Series series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2024 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity