I joined the Computer Science Department at Illinois Tech as an assistant professor in Fall 2024. I am also a member of the IDEAL Institute.
Previously, I was a Postdoctoral Research Fellow supported by the Eric and Wendy Schmidt AI Fellowship in the Department of Electrical and Computer Engineering (ECE) at the University of Michigan, Ann Arbor. I was hosted by Qing Qu, and Wei Hu. Before my postdoc, I completed my PhD in ECE advised by Clay Scott, also at the University of Michigan. Prior to that, I spent two years in the Mathematics Department of UC Davis where I obtained my masters.
* denotes equal contribution.
The Implicit Bias of Gradient Descent on Separable Multiclass Data Hrithik Ravi, Clayton Scott, Daniel Soudry, and Yutong Wang Accepted to Neural Information Processing Systems, 2024. [arXiv]
Sim2Real in Reconstructive Spectroscopy: Deep Learning with Augmented Device-Informed Data Simulation Jiyi Chen*, Pengyu Li*, Yutong Wang, Pei-Cheng Ku, and Qing Qu APL Machine Learning, vol. 2, no. 3, pp. 036106, 2024. [Paper] [arXiv]
Unified Binary and Multiclass Margin-Based Classification Yutong Wang and Clayton Scott Journal of Machine Learning Research, vol. 25, no. 143, pp. 1–51, 2024. [Paper] [arXiv]
Neural Collapse in Multi-label Learning with Pick-all-label Loss Pengyu Li*, Xiao Li*, Yutong Wang, and Qing Qu International Conference on Machine Learning, 2024. [Paper] [arXiv]
Near-Interpolators: Rapid Norm Growth and the Trade-Off between Interpolation and Generalization Yutong Wang, Rishi Sonthalia, Wei Hu Artificial Intelligence and Statistics, 2024. [Paper] [arXiv]
Benign Overfitting and Grokking in ReLU Networks for XOR Cluster Data Zhiwei Xu, Yutong Wang, Spencer Frei, Gal Vardi, and Wei Hu International Conference on Learning Representations, 2024. [OpenReview] [arXiv]
On Classification-Calibration of Gamma-Phi Losses Yutong Wang and Clayton Scott Conference on Learning Theory, 2023. [Paper] [arXiv]
Consistent Interpolating Ensembles via the Manifold-Hilbert Kernel Yutong Wang and Clayton Scott Neural Information Processing Systems, 2022. [OpenReview] [arXiv]
Learning from Label Proportions by Learning with Label Noise Jianxin Zhang, Yutong Wang, and Clayton Scott Neural Information Processing Systems, 2022. [OpenReview] [arXiv]
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]
An exact solver for the Weston-Watkins SVM subproblem Yutong Wang and Clayton Scott International Conference on Machine Learning, 2021. [Paper] [arXiv] [Code]
Weston-Watkins Hinge Loss and Ordered Partitions Yutong Wang and Clayton Scott Neural Information Processing Systems, 2020. [Paper] [arXiv]
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: