Talks and presentations

Training neural ODEs for density estimation

April 23, 2020

Talk, IPAM: Workshop on PDEs and Inverse Problems in Machine Learning, LA, California

Pre-pandemic, I was invited to be a visiting fellow at IPAM’s spring 2020 long program on high-dimensional Hamilton-Jacobi PDEs. Although my stay was cut short, I did give a virtual talk as part of the program’s workshop on PDEs and Inverse Problems in Machine Learning. This talk was based on our paper on training neural ODEs with kinetic regularization

TV Regularization leads to adversarially robust and accurate neural networks

February 26, 2019

Talk, Level Set Collective, UCLA, LA, California

This was an invited talk I gave at the at the Level Set Collective, in the UCLA Math department. This presentation was based off of joint work with Adam Oberman and Bilal Abbasi, where we trained adversarially robust neural networks with both Lipshitz and TV gradient regularization.