Tyler LaBonte

Tyler LaBonte Machine Learning Research Intern at Google X Viterbi Fellow at the University of Southern California t + lastname@usc.edu

About Me

I am a machine learning research intern at Google X and an undergraduate researcher in the Theory Group at USC. I have been fortunate to be advised by Shaddin Dughmi, Jason D. Lee, and David Kempe. Previously, I was a machine learning research intern at Sandia National Laboratories and the Air Force Research Laboratory.

I take a scientific approach to reconcile theory with empirical phenomena in deep learning. I develop fast, scrappy experiments that challenge conventional wisdom, then use the results to guide and revise theoretical hypotheses. My undergraduate research has focused on convex optimization, computer vision, and Bayesian learning.

Education

University of Southern California, 2017–2021
B.S., Applied and Computational Mathematics, magna cum laude
Minor in Computer Science

Research Interests

• Mathematical Foundations of Machine Learning

• Generalization Theory of Deep Learning

• Convex and Non-Convex Optimization

• Online Learning and Bandit Problems

Selected Awards

• Neo Scholar (Top ~100 CS undergrads in America)

• SIMLR Award for Outstanding Intern

• USC Trustee Scholar ($250,000)

• USC Viterbi Fellow ($24,000)

• Dolphin Scholarship ($13,600)

• Admiral Bernard Clarey Memorial Scholarship ($7,000)

Selected Publications

• Quantifying the Unknown: Impact of Segmentation Uncertainty on Image-Based Simulations
  Michael C. Krygier, Tyler LaBonte, Carianne Martinez, Chance Norris, Krish Sharma, Lincoln N. Collins, Partha P. Mukherjee, and Scott A. Roberts
  Under submission to Nature Communications

• We Know Where We Don't Know: 3D Bayesian CNNs for Credible Geometric Uncertainty
  Tyler LaBonte, Carianne Martinez, and Scott A. Roberts
  Preprint