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 in Ann Arbor, 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.

Research

My main research interests involve deep representation learning and nonconvex/manifold optimization. I am also interested in various applied problems such as domain adaptation and inverse problems.

Publications & Preprints

1. Can Yaras*, Peng Wang*, Zhihui Zhu, Laura Balzano, Qing Qu. Neural Collapse with Normalized Features: A Geometric Analysis over the Riemannian Manifold. Accepted at NeurIPS ’22. [arXiv][GitHub]

2. Peng Wang*, Huikang Liu*, Can Yaras*, Laura Balzano, Qing Qu. Linear Convergence Analysis of Neural Collapse with Unconstrained Features. Accepted at NeurIPS ’22 OPT Workshop.

3. Tuba Sarwar, Can Yaras, Xiang Li, Qing Qu, Pei-Cheng Ku. Miniaturizing a Chip-Scale Spectrometer Using Local Strain Engineering and Total-Variation Regularized Reconstruction. ACS Nano Letters.

4. Can Yaras, Bohao Huang, Kyle Bradbury, Jordan M Malof. Randomized Histogram Matching: A Simple Augmentation for Unsupervised Domain Adaptation in Overhead Imagery. [arXiv]