Equations on programs are used to express domain knowledge, verify correctness, and improve performance, by people such as programmers and by tools such as compilers. It turns out that equations on probabilistic programs are a particularly good way to express Bayesian inference, verify distribution correctness, and improve sampler performance. In this way, this tutorial will introduce the mathematical reasoning principles that practitioners of probabilistic reasoning use to turn declarative models into efficient algorithms. These principles include integration and conjugacy, density and conditioning, and detailed balance.

Conference Day
Mon 8 Jan

Displayed time zone: Tijuana, Baja California change

09:00 - 10:30
Equational reasoning for probabilistic programmingTutorialFest at Bradbury
09:00
90m
Talk
Equational reasoning for probabilistic programming.
TutorialFest
A: Chung-chieh ShanIndiana University, USA
Media Attached
11:00 - 12:00
Equational reasoning for probabilistic programmingTutorialFest at Bradbury
11:00
60m
Talk
Equational reasoning for probabilistic programming.
TutorialFest
A: Chung-chieh ShanIndiana University, USA
Media Attached