Robust Simulation-Based Inference in Cosmology with Bayesian Neural Networks
This addresses reliability issues in cosmological data analysis for researchers, but is incremental as it adapts an existing Bayesian method to a specific domain.
The paper tackles the problem of simulation-based inference (SBI) in cosmology being vulnerable to generalization issues due to imperfect simulations and limited training data, and shows that using a Bayesian neural network framework mitigates biases and improves reliability outside the training set, as applied to cosmic microwave background inference.
Simulation-based inference (SBI) is rapidly establishing itself as a standard machine learning technique for analyzing data in cosmological surveys. Despite continual improvements to the quality of density estimation by learned models, applications of such techniques to real data are entirely reliant on the generalization power of neural networks far outside the training distribution, which is mostly unconstrained. Due to the imperfections in scientist-created simulations, and the large computational expense of generating all possible parameter combinations, SBI methods in cosmology are vulnerable to such generalization issues. Here, we discuss the effects of both issues, and show how using a Bayesian neural network framework for training SBI can mitigate biases, and result in more reliable inference outside the training set. We introduce cosmoSWAG, the first application of Stochastic Weight Averaging to cosmology, and apply it to SBI trained for inference on the cosmic microwave background.