Aaron Defazio

Postdoctoral Researcher

Born in Australia, I completed my undergraduate studies at the Australian National University (ANU) in Canberra, where I completed a bachelor’s in computer science (hons). I received a University Medal for graduating at the top of my class. I did my PhD on “New Optimization Methods for Machine Learning” at ANU in Australia in collaboration with the research group NICTA/DATA61. I have experience working on applied problems as a consultant data scientist, as well as basic research.


Optimization, Bayesian techniques, graph structure inference, and data science

Related Links


Latest Publications

arXiv - January 29, 2020

fastMRI: An Open Dataset and Benchmarks for Accelerated MRI

Jure Zbontar, Florian Knoll, Anuroop Sriram, Tullie Murrell, Zhengnan Huang, Matthew J. Muckley, Aaron Defazio, Ruben Stern, Patricia Johnson, Mary Bruno, Marc Parente, Krzysztof J. Geras, Joe Katsnelson, Hersh Chandarana, Zizhao Zhang, Michal Drozdzal, Adriana Romero, Michael Rabbat, Pascal Vincent, Nafissa Yakubova, James Pinkerton, Duo Wang, Erich Owens, Larry Zitnick, Michael P. Recht, Daniel K. Sodickson, Yvonne W. Lui

NeurIPS - December 8, 2019

On the Curved Geometry of Accelerated Optimization

Aaron Defazio

NeurIPS - December 8, 2019

On the Ineffectiveness of Variance Reduced Optimization for Deep Learning

Aaron Defazio, Léon Bottou