Applied Measure Theory for Probabilistic Modeling
2021-07-30, 19:00–19:30 (UTC), Purple

We'll give an overview of MeasureTheory.jl, describing some of the advantages relative to Distributions.jl and some applications in probabilistic modeling.


We have several goals for MeasureTheory.jl:
- Better performance than Distributions.jl, because normalizing constants can be deferred
- Minimal type constraints, for example allowing symbolic manipulations
- Autodiff-friendly code
- Multiple parameterizations for a given measure
- A consistent interface, especially important for probabilistic programming
- Composability, to make it easy to build new measures from existing ones
- Fall-back to Distributions.jl when needed

While the library is still in its early stages, we're making good progress on all fronts. We hope this can become the library of choice as a basis for probabilistic modeling in Julia, and we're excited to help the Julia community get involved in development.

Hi, I'm Chad. My interests range from applied problems through "technology transfer", to applied research. I've been involved in probabilistic programming for the last ten years, and have led design of a few prototype systems. Since 2015 I've been very interested in Julia, resulting in Soss.jl and MeasureTheory.jl, as well as some utility packages around these.

Most recently I've founded Informative Prior, where I'm available for contract consulting work involving teaching, development, or application of probabilistic modeling software.

This speaker also appears in: