Alex Beatson

abeatson -at- cs.princeton.edu

Google Scholar  /  Twitter  /  Resume


I'm a PhD student in computer science at Princeton University, advised by Ryan P. Adams.

My research interests are in deep learning, probabilistic modelling, stochastic estimation, and numerical methods. I'm interested in carefully combining these tools to accelerate modelling, optimization, and design across machine learning, engineering, and scientific computing. I often work on ML techniques which embody known properties from physics, which integrate with numerical methods, or which take advantage of the underlying computational structure of numerical methods to more efficiently solve a given problem.

I spent two fun summers at Google: at Google Brain in Zurich, working on AutoML for generative models with Sylvain Gelly, Olivier Teytaud, and Karol Kurach; and with the speech recognition team in New York, working on transfer learning with Pedro Moreno.

Previously, I received my Master's from Princeton advised by Han Liu, working on information theoretic security of machine learning. I did my B.Eng at the University of Canterbury in New Zealand, where I worked with Geoff Chase on signal processing for ventilators in the intensive care unit. Between college and graduate school I worked with Dominic Lee and Raazesh Sainudiin on anomaly detection algorithms at the cybersecurity startup Cognevo, which was since acquired by Telstra.

Recent papers

Learning composable energy surrogates for PDE order reduction
Alex Beatson, Jordan T. Ash, Geoffrey Roeder, Tianju Xue, Ryan P. Adams.
In submission, 2020.

Amortized finite element analysis for fast PDE-constrained optimization
Tianju Xue, Alex Beatson, Sigrid Adriaenssens, Ryan P. Adams.
In submission, 2020. Preprint at ICLR DeepDiffEq, 2020.

SUMO: Unbiased estimation of log marginal probability for latent variable models
Yucen Luo, Alex Beatson, Mohammad Norouzi, Jun Zhu, David Duvenaud, Ryan P. Adams, Ricky T. Q. Chen.
ICLR, 2020.

Efficient optimization of loops and limits with randomized telescoping sums
Alex Beatson, Ryan P. Adams.
ICML, 2019.

Amortized Bayesian meta-learning
Sachin Ravi, Alex Beatson.
ICLR, 2019.