Aaron Defazio

New York City, United States

Aaron's research focuses on improving the practice of machine learning through the development of more reliable and theoretically sound methods such as performance optimization, initialization, and normalization. He also drives current research frontiers in applied areas and is currently involved in MRI imaging reconstruction and automated theorem proving.

Aaron's Publications

December 08, 2019

Research

On the Curved Geometry of Accelerated Optimization

Duc Le, Xiaohui Zhang, Weiyi Zhang, Christian Fuegen, Geoffrey Zweig, Michael L. Seltzer

December 08, 2019

December 08, 2019

Research

On the Ineffectiveness of Variance Reduced Optimization for Deep Learning

Aaron Defazio, Leon Bottou

December 08, 2019