Evan W. Becker

Evan W. Becker

PhD Student in Computer Science

University of California, Los Angeles (UCLA)


I am a PhD student at the University of California, Los Angeles (UCLA) in the Department of Computer Science, advised by Alyson Fletcher and Sundeep Rangan. My current research is focused on understanding the training dynamics of deep generative models in high-dimensional regimes. I am especially interested in the implicit bias and regularization of deep learning, as well as uncovering necessary conditions for convergence and generalization. I am currently funded by an Amazon Science PhD Fellowship.

Previously I was a Stamps Scholar at the University of Pittsburgh and earned a B.Sc. in Electrical Engineering in 2020.

Download my cv .

  • Generative Models
  • Deep Learning Theory
  • High-Dimensional Statistics
  • PhD in Computer Science, Prospective

    University of California, Los Angeles

  • BSc in Electrical Engineering, 2020

    University of Pittsburgh

Recent Publications

Check out my recent publications!

(2023). High Probability Bounds for Stochastic Continuous Submodular Maximization. International Conference on Artificial Intelligence and Statistics.


(2023). Local Convergence of Gradient Descent-Ascent for Training Generative Adversarial Networks. arXiv preprint arXiv:2305.08277.


(2022). Conditioned Spatial Downscaling of Climate Variables. NeurIPS 2022 AI for Science: Progress and Promises.

Cite URL

(2022). Instability and Local Minima in GAN Training with Kernel Discriminators. In NeurIPS.

Cite URL Video