Nesting Particle Filters for Experimental Design in Dynamical Systems

Sahel Iqbal, Adrien Corenflos, Simo Särkkä, Hany Abdulsamad
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:21047-21068, 2024.

Abstract

In this paper, we propose a novel approach to Bayesian experimental design for non-exchangeable data that formulates it as risk-sensitive policy optimization. We develop the Inside-Out SMC$^2$ algorithm, a nested sequential Monte Carlo technique to infer optimal designs, and embed it into a particle Markov chain Monte Carlo framework to perform gradient-based policy amortization. Our approach is distinct from other amortized experimental design techniques, as it does not rely on contrastive estimators. Numerical validation on a set of dynamical systems showcases the efficacy of our method in comparison to other state-of-the-art strategies.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-iqbal24a, title = {Nesting Particle Filters for Experimental Design in Dynamical Systems}, author = {Iqbal, Sahel and Corenflos, Adrien and S\"{a}rkk\"{a}, Simo and Abdulsamad, Hany}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {21047--21068}, 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/iqbal24a/iqbal24a.pdf}, url = {https://proceedings.mlr.press/v235/iqbal24a.html}, abstract = {In this paper, we propose a novel approach to Bayesian experimental design for non-exchangeable data that formulates it as risk-sensitive policy optimization. We develop the Inside-Out SMC$^2$ algorithm, a nested sequential Monte Carlo technique to infer optimal designs, and embed it into a particle Markov chain Monte Carlo framework to perform gradient-based policy amortization. Our approach is distinct from other amortized experimental design techniques, as it does not rely on contrastive estimators. Numerical validation on a set of dynamical systems showcases the efficacy of our method in comparison to other state-of-the-art strategies.} }
Endnote
%0 Conference Paper %T Nesting Particle Filters for Experimental Design in Dynamical Systems %A Sahel Iqbal %A Adrien Corenflos %A Simo Särkkä %A Hany Abdulsamad %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-iqbal24a %I PMLR %P 21047--21068 %U https://proceedings.mlr.press/v235/iqbal24a.html %V 235 %X In this paper, we propose a novel approach to Bayesian experimental design for non-exchangeable data that formulates it as risk-sensitive policy optimization. We develop the Inside-Out SMC$^2$ algorithm, a nested sequential Monte Carlo technique to infer optimal designs, and embed it into a particle Markov chain Monte Carlo framework to perform gradient-based policy amortization. Our approach is distinct from other amortized experimental design techniques, as it does not rely on contrastive estimators. Numerical validation on a set of dynamical systems showcases the efficacy of our method in comparison to other state-of-the-art strategies.
APA
Iqbal, S., Corenflos, A., Särkkä, S. & Abdulsamad, H.. (2024). Nesting Particle Filters for Experimental Design in Dynamical Systems. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:21047-21068 Available from https://proceedings.mlr.press/v235/iqbal24a.html.

Related Material