Jonathan P. Chen

Machine Learning Researcher
me [@]

I am a research scientist at Uber AI Labs in San Francisco, CA. My area of interest is in statistical machine learning and probabilistic programming, and their applications in cognitive science, vision, and language. I seek to reverse-engineer the process in which humans reason about the world around them.

I work on the probabilistic programming language Pyro. I also work on computer vision and perception in building maps for self-driving cars. I received my undergraduate degree in computer science from the University of Pennsylvania.

I've recently begun maintaining a research and a personal blog!



Joint Mapping and Calibration via Differentiable Sensor Fusion
Jonathan P. Chen*, Fritz Obermeyer*, Vlad Lyapunov, Lionel Gueguen, Noah Goodman.
In submission.
*Equal Contribution.


Improving Automated Variational Inference with Normalizing Flows
Stefan Webb, Jonathan P. Chen, Martin Jankowiak, Noah D. Goodman.
ICML AutoML Workshop, 2019.

Pyro: Deep Universal Probabilistic Programming
Eli Bingham, Jonathan P. Chen, Martin Jankowiak, Neeraj Pradhan, Theofanis Karaletsos, Rohit Singh, Paul Szerlip, Paul Horsfall, Noah D. Goodman.
Journal of Machine Learning Research, 2018.
Transpiling Stan models to Pyro
Jonathan P. Chen, Rohit Singh, Eli Bingham, Noah Goodman.
The International Conference on Probabilistic Programming (PROBPROG), 2018.

Open Source Software

Pyro is a deep, universal probabilistic programming language written in Python on top of PyTorch. For more information, check out the release blog.

Pyro-Stan Compiler
C++ Compiler that compiles Stan models into Pyro models. Validated on a corpus of 130+ models.

Torch JS
Implementation of adnn, a Javascript tensor and reverse-mode automatic differentiation library in Torch.


System and Method for Object Location Detection from Imagery
Fritz Obermeyer, Jonathan P. Chen, Vladimir Lyapunov, Lionel Gueguen, Noah Goodman, Ben Kadlec, Douglas Bemis.
US Provisional Patent, 62/718,985. 2018.