Theofanis Karaletsos

Research Scientist

I work on probabilistic machine learning, deep learning, and probabilistic programming in the Uncertainty team within Probability at Facebook.

In my recent work, I have focused on researching Bayesian Neural Networks and decision making under Uncertainty. I am interested in building data-efficient systems that are aware of and utilize their own uncertainty.

In my past, I was a researcher and at Uber AI Labs and startup Geometric Intelligence, where I contributed to projects such as the Pyro probabilistic programming language ( ). I have previously worked on probabilistic modeling & ML for Biology, Healthcare, and Computer Vision applications.


Probabilistic modeling and probabilistic programming, Bayesian inference, deep learning, decision making under uncertainty

Latest Publications

ICML - July 18, 2021

Variational Auto-Regressive Gaussian Processes for Continual Learning

Sanyam Kapoor, Theofanis Karaletsos, Thang D. Bui

NeurIPS - December 6, 2020

Hierarchical Gaussian Process Priors for Bayesian Neural Network Weights

Theofanis Karaletsos, Thang D. Bui