← Search

Stephen R Green

2 accepted papers

2023

Flow Matching for Scalable Simulation-Based Inference

NeurIPS 2023poster

Neural posterior estimation methods based on discrete normalizing flows have become established tools for simulation-based inference (SBI), but scaling them to high-dimensional problems can be challenging. Building on recent advances in generative modeling, we here present flow matching posterior es…

2022

Group equivariant neural posterior estimation

ICLR 2022poster

Simulation-based inference with conditional neural density estimators is a powerful approach to solving inverse problems in science. However, these methods typically treat the underlying forward model as a black box, with no way to exploit geometric properties such as equivariances. Equivariances ar…