ReddingStan smuggles log probabilities and gradients out of a Stan program. It’s meant to facilitate algorithmic prototyping.
Originally published here: https://bayesianops.medium.com/stan-algorithms-where-to-start-e6103c778d12 We’re starting the work that’s involved with Reimplementing the Inference Algorithms in Stan. Before we can get to any reimplementation, we need to understand what’s going on. The first steps are to identify the entry point into the code, instantiate the existing tests, and take inventory of what’s there. I have Michael … Continue reading Stan Algorithms: Where to Start?
I’ve wanted to rewrite the inference algorithms in Stan for many years. It’s one of those things that was never urgent enough to warrant the effort, but entering 2022, I have some spare time that I will dedicate to this project. (Also, publicly writing this down will force me to work on it.) Photo by … Continue reading Reimplementing the Inference Algorithms in Stan
Recently Tadej Ciglarič came up with a new pattern to do automatic differentiation in Stan Math's C++ library and I thought it would be nice to have a little blog post talking about it. For the purposes of blogging I'm going to be simplifying a few things, but the main take here is that it's … Continue reading Thinking About Automatic Differentiation in Fun New Ways