Can Yaras


PhD Student
Electrical and Computer Engineering
University of Michigan - Ann Arbor
Email: cjyaras [at] umich [dot] edu

[Google Scholar][GitHub]

About Me

I am a second-year PhD student in Electrical and Computer Engineering at the University of Michigan, co-advised by Qing Qu and Laura Balzano. I received my undergraduate degree from Duke University in Electrical and Computer Engineering, along with a major in Mathematics and a minor in Computer Science.

I am spending the summer at Google NYC as a student researcher, hosted by Chong You.


My main research interests involve characterizing low-dimensional geometry and dynamics in deep neural networks through the lens of optimization, and applying those insights towards elucidating representation learning and improving the efficiency of deep learning. I am also generally interested in nonconvex/manifold optimization, as well as various applied ML problems.

Publications & Preprints

  1. C. Yaras*, P. Wang*, W. Hu, Z. Zhu, L. Balzano, Q. Qu. The Law of Parsimony in Gradient Descent for Learning Deep Linear Networks. Preprint. [paper] [code]

  2. C. Yaras*, P. Wang*, Z. Zhu, L. Balzano, Q. Qu. Neural Collapse with Normalized Features: A Geometric Analysis over the Riemannian Manifold. NeurIPS ’22. [paper] [code]

  3. P. Wang*, H. Liu*, C. Yaras*, L. Balzano, Q. Qu. Linear Convergence Analysis of Neural Collapse with Unconstrained Features. NeurIPS ’22 OPT Workshop. [paper]

  4. T. Sarwar, C. Yaras, X. Li, Q. Qu, P.C. Ku. Miniaturizing a Chip-Scale Spectrometer Using Local Strain Engineering and Total-Variation Regularized Reconstruction. ACS Nano Letters. [paper]

  5. C. Yaras, B. Huang, K. Bradbury, J.M. Malof. Randomized Histogram Matching: A Simple Augmentation for Unsupervised Domain Adaptation in Overhead Imagery. Preprint. [paper]