About us

This site is maintained by Kyle Cranmer and Jason Lo. We are committed to turning this site into a valuable community resource. We’re dedicated to collecting recent research papers on methodological developments and applications in the field of simulation-based inference. Our vision is to create a crowd-sourced platform, where users can access and contribute to the latest knowledge in this domain. It will probably be similar to IRIS-HEP webpages (source) and/or something like this living review.

Out site is in its early infancy. As we continue to build and refine the infrastructure, we appreciate your understanding and patience. While we have laid the groundwork for this community resource, there is still much to be done to realize its full potential. In these initial stages, we encourage users to provide feedback, suggest improvements, and participate in the platform’s growth. By acknowledging its current limitations and working together, we can create a comprehensive, well-organized, and user-friendly hub for all things related to simulation-based inference. The success of this platform depends on the collaborative efforts of our community, and we are excited to embark on this journey with you. If you’re passionate about simulation-based inference and would like to join our mission, we invite you to submit Pull Requests (PRs) to our GitHub repository. Your contributions could include adding new research papers, improving the categorization of resources, enhancing our platform’s features, or offering insights to foster methodological advancements. By contributing to our project, you’ll become an essential part of the community, helping to shape the future of simulation-based inference. We value every submission and appreciate the time and effort invested by our contributors. Together, we can create a powerful, inclusive resource that benefits researchers, practitioners, and enthusiasts alike.

To keep our project interesting, we occasionally introduce innovative approaches to tackle different issues on our website. One of our latest experiments involved leveraging the rapidly growing ChatGPT, which we used to auto-label the papers we’ve collected in our backend. The outcomes have certainly exceeded expectations. For those curious about the mechanics behind our website, feel free to explore our GitHub repository. And perhaps consider contributing to it.

Latest Posts

J Roulet, T Venumadhav - arXiv preprint arXiv:2402.11439, 2024 - arxiv.org

This review provides a conceptual and technical survey of methods for parameter estimation of gravitational wave signals in ground-based interferometers such as LIGO …

J Linhart, GV Cardoso, A Gramfort, S Le Corff… - 2024 - hal.science

… Simulation-based inference (SBI) stands out in this context by only requiring a dataset of simulations to train deep generative models capable of approximating the …

A Ghosh - Bulletin of the American Physical Society, 2024 - APS

Neural Simulation-Based Inference (NSBI) is a powerful class of machine learning (ML)-based methods for statistical inference that naturally handles high-dimensional …

H Jia - Bulletin of the American Physical Society, 2024 - APS

… We introduce Neural Quantile Estimation (NQE), a novel Simulation-Based Inference method based on conditional quantile regression, and its application to the field level …