Brett Larsen

Headshot.jpg

I am a PhD candidate in the Neural Dynamics and Computation Lab at Stanford University co-advised by Shaul Druckmann and Surya Ganguli. My work received generous funding from a DOE Computational Science Graduate Fellowship, and through this program, I had the opportunity to intern with Sandia National Labs’ Extreme-Scale Data Science group and frequently collaborate with Tammy Kolda.

My research combines theoretical and empirical approaches to understand and improve deep learning, low-rank models, and recurrent networks in the brain. This has led to the opportunity to work with many excellent collaborators, including Jonathan Frankle, Karolina Dziugaite, Stanislav Fort, Alex Williams, and Scott Linderman.

Prior to my PhD, I completed the MPhil in Scientific Computing (Machine Learning Focus) at the University of Cambridge working with Carola Bibiane Schönlieb and Martin Benning. I did my undergrad at Arizona State University and Barrett, the Honors College where I worked on statistical signal processing.

Contact: bwlarsen [at] stanford.edu

Interests

  • Machine Learning and Data Science
  • High-Dimensional Loss Landscapes
  • Numerical Optimization
  • Randomized Algorithms
  • Low-Rank Models
  • Robust Statistics

Education

  • PhD in Physics, In progress

    MS in Statistics, 2020

    Stanford University

  • MPhil in Scientific Computing, 2016

    University of Cambridge

  • BSE in Electrical Engineering, 2015

    BS in Physics, 2015

    Arizona State University (ASU)