iiinova — where your digital self keeps evolving

Reposted by Ryan Kelly

Paul Bürkner @paulbuerkner.com · 22/11/2024

The beta version of BayesFlow 2.0 is becoming more powerful and stable by the day. If you are curious about Amortized Bayesian Inference, give BayesFlow a try! github.com/bayesflow-or...

github.com

GitHub - bayesflow-org/bayesflow at dev

A Python library for amortized Bayesian workflows using generative neural networks. - GitHub - bayesflow-org/bayesflow at dev

512125

Ryan Kelly @ryanpkelly.bsky.social · 21/11/2024

Thrilled to contribute to this work led by David Frazier providing theory for NPE/NLE in simulation-based inference. These methods are known to match the accuracy of ABC and BSL with fewer simulations, this paper rigorously shows why this can be achieved. arxiv.org/abs/2411.12068

arxiv.org

The Statistical Accuracy of Neural Posterior and Likelihood Estimation

Neural posterior estimation (NPE) and neural likelihood estimation (NLE) are machine learning approaches that provide accurate posterior, and likelihood, approximations in complex modeling scenarios, ...

55411

Reposted by Ryan Kelly

Marvin Schmitt @marvin-schmitt.com · 17/11/2024

I created a starter pack for simulation-based inference (aka. likelihood-free inference). Let me know if you’d like me to add you. go.bsky.app/GVnJRoK

164218

Reposted by Ryan Kelly

Maarten van Smeden @maartenvsmeden.bsky.social · 18/11/2024

I made one for stats papers

15542148