I am a Postdoctoral Research Fellow in the Department of Electrical and Computer Engineering (ECE) at the University of Michigan, Ann Arbor. My advisors are Professors Qing Qu, and Wei Hu. My research interests are in theoretical machine learning. I also work on applications of machine learning to reconstructive spectroscopy systems and semiconductor devices, in collaboration with the research group of Professor Pei-Cheng Ku. I am grateful to be supported by the Eric and Wendy Schmidt AI Fellowship.
Before my postdoc, I completed my PhD in ECE advised by Professor Clay Scott, also at the University of Michigan. Prior to my PhD, I obtained my masters in mathematics at UC Davis.
Unified Binary and Multiclass Margin-Based Classification Yutong Wang and Clayton Scott [arXiv]
Neural Collapse in Multi-label Learning with Pick-all-label Loss Pengyu Li*, Yutong Wang*, Xiao Li, and Qing Qu [arXiv]
Benign Overfitting and Grokking in ReLU Networks for XOR Cluster Data Zhiwei Xu, Yutong Wang, Spencer Frei, Gal Vardi, and Wei Hu [arXiv]
* denotes equal contribution.
VC dimension of partially quantized neural networks in the overparametrized regime Yutong Wang and Clayton Scott International Conference on Learning Representations, 2022. [OpenReview] [arXiv] [Code]
Hybrid Stem Cell States: Insights Into the Relationship Between Mammary Development and Breast Cancer Using Single-Cell Transcriptomics Tasha Thong, Yutong Wang, Michael D. Brooks, Christopher T. Lee, Clayton Scott, Laura Balzano, Max S. Wicha, and Justin A. Colacino Frontiers in Cell and Developmental Biology. [Paper] [Supporting technical report]
All about SVMs: