Ryan Kelly

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...

Thanks Marvin! Great to hear you had a chance to discuss it with David down in Aus.

Thanks!

Thanks Ayush!

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, ...

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

Thanks Umberto!

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

I made one for stats papers