An amortized approach to non-linear mixed-effects modeling based on neural posterior estimation

Jonas Arruda, Yannik Schälte, Clemens Peiter, Olga Teplytska, Ulrich Jaehde, Jan Hasenauer
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:1865-1901, 2024.

Abstract

Non-linear mixed-effects models are a powerful tool for studying heterogeneous populations in various fields, including biology, medicine, economics, and engineering. Here, the aim is to find a distribution over the parameters that describe the whole population using a model that can generate simulations for an individual of that population. However, fitting these distributions to data is computationally challenging if the description of individuals is complex and the population is large. To address this issue, we propose a novel machine learning-based approach: We exploit neural density estimation based on conditional normalizing flows to approximate individual-specific posterior distributions in an amortized fashion, thereby allowing for efficient inference of population parameters. Applying this approach to problems from cell biology and pharmacology, we demonstrate its unseen flexibility and scalability to large data sets compared to established methods.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-arruda24a, title = {An amortized approach to non-linear mixed-effects modeling based on neural posterior estimation}, author = {Arruda, Jonas and Sch\"{a}lte, Yannik and Peiter, Clemens and Teplytska, Olga and Jaehde, Ulrich and Hasenauer, Jan}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {1865--1901}, year = {2024}, editor = {Salakhutdinov, Ruslan and Kolter, Zico and Heller, Katherine and Weller, Adrian and Oliver, Nuria and Scarlett, Jonathan and Berkenkamp, Felix}, volume = {235}, series = {Proceedings of Machine Learning Research}, month = {21--27 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v235/main/assets/arruda24a/arruda24a.pdf}, url = {https://proceedings.mlr.press/v235/arruda24a.html}, abstract = {Non-linear mixed-effects models are a powerful tool for studying heterogeneous populations in various fields, including biology, medicine, economics, and engineering. Here, the aim is to find a distribution over the parameters that describe the whole population using a model that can generate simulations for an individual of that population. However, fitting these distributions to data is computationally challenging if the description of individuals is complex and the population is large. To address this issue, we propose a novel machine learning-based approach: We exploit neural density estimation based on conditional normalizing flows to approximate individual-specific posterior distributions in an amortized fashion, thereby allowing for efficient inference of population parameters. Applying this approach to problems from cell biology and pharmacology, we demonstrate its unseen flexibility and scalability to large data sets compared to established methods.} }
Endnote
%0 Conference Paper %T An amortized approach to non-linear mixed-effects modeling based on neural posterior estimation %A Jonas Arruda %A Yannik Schälte %A Clemens Peiter %A Olga Teplytska %A Ulrich Jaehde %A Jan Hasenauer %B Proceedings of the 41st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Ruslan Salakhutdinov %E Zico Kolter %E Katherine Heller %E Adrian Weller %E Nuria Oliver %E Jonathan Scarlett %E Felix Berkenkamp %F pmlr-v235-arruda24a %I PMLR %P 1865--1901 %U https://proceedings.mlr.press/v235/arruda24a.html %V 235 %X Non-linear mixed-effects models are a powerful tool for studying heterogeneous populations in various fields, including biology, medicine, economics, and engineering. Here, the aim is to find a distribution over the parameters that describe the whole population using a model that can generate simulations for an individual of that population. However, fitting these distributions to data is computationally challenging if the description of individuals is complex and the population is large. To address this issue, we propose a novel machine learning-based approach: We exploit neural density estimation based on conditional normalizing flows to approximate individual-specific posterior distributions in an amortized fashion, thereby allowing for efficient inference of population parameters. Applying this approach to problems from cell biology and pharmacology, we demonstrate its unseen flexibility and scalability to large data sets compared to established methods.
APA
Arruda, J., Schälte, Y., Peiter, C., Teplytska, O., Jaehde, U. & Hasenauer, J.. (2024). An amortized approach to non-linear mixed-effects modeling based on neural posterior estimation. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:1865-1901 Available from https://proceedings.mlr.press/v235/arruda24a.html.

Related Material