Ryan Kelly
@ryanpkelly.bsky.social
PhD student at QUT in computational Bayesian statistics
simulation-based inference | generative modelling | robust ML
simulation-based inference | generative modelling | robust ML
Reposted by 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...
github.com/bayesflow-or...
GitHub - bayesflow-org/bayesflow at dev
A Python library for amortized Bayesian workflows using generative neural networks. - GitHub - bayesflow-org/bayesflow at dev
github.com
November 22, 2024 at 8:52 AM
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/bayesflow-or...
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/abs/2411.12068
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, ...
arxiv.org
November 21, 2024 at 6:04 AM
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/abs/2411.12068
Reposted by Ryan Kelly
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
Let me know if you’d like me to add you.
go.bsky.app/GVnJRoK
November 17, 2024 at 3:14 PM
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
Let me know if you’d like me to add you.
go.bsky.app/GVnJRoK
Reposted by Ryan Kelly
I made one for stats papers
November 18, 2024 at 4:02 AM
I made one for stats papers