BayesFlow: Amortized Bayesian Workflows With Neural Networks
This provides a tool for researchers and practitioners in Bayesian statistics to accelerate inference tasks, though it is incremental as it builds on existing neural network architectures.
The authors tackled the problem of approximating intractable posterior distributions and comparing competing models in Bayesian workflows by introducing BayesFlow, a Python library for simulation-based training of neural networks for amortized Bayesian inference, enabling almost instantaneous inference after upfront training.
Modern Bayesian inference involves a mixture of computational techniques for estimating, validating, and drawing conclusions from probabilistic models as part of principled workflows for data analysis. Typical problems in Bayesian workflows are the approximation of intractable posterior distributions for diverse model types and the comparison of competing models of the same process in terms of their complexity and predictive performance. This manuscript introduces the Python library BayesFlow for simulation-based training of established neural network architectures for amortized data compression and inference. Amortized Bayesian inference, 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. Since the trained networks can perform inference almost instantaneously, the upfront neural network training is quickly amortized.