Skip to footer

Fritz Obermeyer

Fritz Obermeyer
2 BLOG ARTICLES 4 RESEARCH PAPERS
Fritz is a research engineer at Uber AI focusing on probabilistic programming. He is the engineering lead for the Pyro team.

Engineering Blog Articles

Pyro Accepted by the LF Deep Learning Foundation as a Hosted Project

Created by Uber in 2017, Pyro was voted in by the Linux Foundation Deep Learning Technical Board as the latest incubation project to join its foundation.

Modeling Censored Time-to-Event Data Using Pyro, an Open Source Probabilistic Programming Language

Censored time-to-event data is critical to the proper modeling and understanding of customer engagement on the Uber platform. In this article, we demonstrate an easier way to model this data using Pyro.

Research Papers

Joint Mapping and Calibration via Differentiable Sensor Fusion

J. Chen, F. Obermeyer, V. Lyapunov, L. Gueguen, N. Goodman
We leverage automatic differentiation (AD) and probabilistic programming to develop an end-to-end optimization algorithm for batch triangulation of a large number of unknown objects. Given noisy detections extracted from noisily geo-located street level imagery without depth information, we jointly estimate the number and location of objects of different types, together with parameters for sensor noise characteristics and prior distribution of objects conditioned on side information. [...] [PDF at arXiv]
Computer Vision and Pattern Recognition (CVPR), 2018

Pyro: Deep Universal Probabilistic Programming

E. Bingham, J. Chen, M. Jankowiak, F. Obermeyer, N. Pradhan, T. Karaletsos, R. Singh, P. Szerlip, P. Horsfall, N. Goodman
Pyro is a probabilistic programming language built on Python as a platform for developing advanced probabilistic models in AI research. [...] [PDF at arXiv]
Journal of Machine Learning Research (JMLR), 2018

Pathwise Derivatives Beyond the Reparameterization Trick

M. Jankowiak, F. Obermeyer
We observe that gradients computed via the reparameterization trick are in direct correspondence with solutions of the transport equation in the formalism of optimal transport. We use this perspective to compute (approximate) pathwise gradients for probability distributions not directly amenable to the reparameterization trick: Gamma, Beta, and Dirichlet. [...] [PDF at arXiv]
International Conference on Machine Learning (ICML), 2018

Characterizing how Visual Question Answering models scale with the world

E. Bingham, P. Molino, P. Szerlip, F. Obermeyer, N. Goodman
Detecting differences in generalization ability between models for visual question answering tasks has proven to be surprisingly difficult. We propose a new statistic, asymptotic sample complexity, for model comparison, and construct a synthetic data distribution to compare a strong baseline CNN-LSTM model to a structured neural network with powerful inductive biases. [...] [PDF at Github]
ViGIL @ NeurIPS(NeurIPS), 2017

Popular Articles