Lars Kuehmichel (TU Dortmund University)

Friday Jun 13, 2025, 11:00 AM → 12:00 PM America/New_York

3rd Floor Conference Room (162 Fifth Avenue )

Discussion Lead: Lars Kuehmichel (TU Dortmund University)

Topics: BayesFlow: Amortized Bayesian Workflows with Neural Networks

Abstract: BayesFlow provides a framework for simulation-based training of established neural network architectures, such as transformers (Vaswani et al., 2017) and normalizing flows (Papamakarios et al., 2021), for amortized data compression and inference. Amortized Bayesian inference (ABI), as implemented in BayesFlow, enables users to train custom neural networks on model simulations and re-use these networks for any subsequent application of the models

Link: https://joss.theoj.org/papers/10.21105/joss.05702.pdf

 

Zoom: Join from PC, Mac, Linux, iOS or Android: https://simonsfoundation.zoom.us/j/460282175?pwd=NncrVXNVb0xKdFF2b0pGLzByOEJMZz09

 Passcode: 162 020