From automatic differentiation to message passing

Invited talk at the Advances and challenges in Machine Learning Languages workshop (ACMLL 2019)
A shorter version appeared in EuroAD 2019

Automatic differentiation is an elegant technique for converting a computable function expressed as a program into a derivative-computing program with similar time complexity. It does not execute the original program as a black-box, nor does it expand the program into a mathematical formula, both of which would be counter-productive. By generalizing this technique, you can produce efficient algorithms for constraint satisfaction, optimization, and Bayesian inference on models specified as programs. This approach can be broadly described as compiling into a message-passing program.

pdf slides . video
Tom Minka