ODEs, approximate Bayesian inference, and ArviZ: A tour of the new features.
ODEs, approximate Bayesian inference, and ArviZ: A tour of the new features.
Four chains isn’t cool. You know what’s cool? A million chains.
I added a working tour of 9 probabilistic programming languages in Python. Code to get it all to run is here (though you are on your own installing all the correct frameworks), and issues/corrections/suggestions are all happily appreciated!
This is also in the “talks” section, but I put a lot of work into it and I think it looks beautiful, so want to highlight it. Read the essay here, which also has link to the slides and source code for generating all the animations.
Higher order integrators do not help too much
Automatically finding a scale for your sampler
Motivation, and an implementation in about 20 lines
Notes and examples for working with automatic differentiation
TensorFlow-2.0 and matplotlib applied to do Carmo’s Riemannian Geometry