University of Cambridge > Talks.cam > Isaac Newton Institute Seminar Series > Amortized Bayesian experimental design with sequential Monte Carlo

Amortized Bayesian experimental design with sequential Monte Carlo

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

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

RCLW03 - Accelerating statistical inference and experimental design with machine learning

Most existing works on amortized Bayesian experimental design (BED) rely on contrastive estimators of the expected information gain (EIG). In this talk, I introduce a new framework for BED grounded in the control-as-inference paradigm. The task of collecting informative trajectories is reframed as a sampling problem from a non-Markovian state-space model. To address the resulting inference challenges, I present a nested sequential Monte Carlo algorithm tailored to this setting. This approach offers a fresh perspective on BED , and we end with ideas for improving the scalability of this algorithm.

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.

 

© 2006-2025 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity