关注
Can Yaras
Can Yaras
在 umich.edu 的电子邮件经过验证 - 首页
标题
引用次数
引用次数
年份
Neural collapse with normalized features: A geometric analysis over the riemannian manifold
C Yaras, P Wang, Z Zhu, L Balzano, Q Qu
Advances in neural information processing systems 35, 11547-11560, 2022
432022
Randomized histogram matching: A simple augmentation for unsupervised domain adaptation in overhead imagery
C Yaras, K Kassaw, B Huang, K Bradbury, JM Malof
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2023
182023
Linear Convergence Analysis of Neural Collapse with Unconstrained Features
P Wang, H Liu, C Yaras, L Balzano, Q Qu
OPT 2022: Optimization for Machine Learning (NeurIPS 2022 Workshop), 0
17*
The law of parsimony in gradient descent for learning deep linear networks
C Yaras, P Wang, W Hu, Z Zhu, L Balzano, Q Qu
arXiv preprint arXiv:2306.01154, 2023
132023
Understanding deep representation learning via layerwise feature compression and discrimination
P Wang, X Li, C Yaras, Z Zhu, L Balzano, W Hu, Q Qu
arXiv preprint arXiv:2311.02960, 2023
112023
Compressible Dynamics in Deep Overparameterized Low-Rank Learning & Adaptation
C Yaras, P Wang, L Balzano, Q Qu
arXiv preprint arXiv:2406.04112, 2024
92024
Miniaturizing a chip-scale spectrometer using local strain engineering and total-variation regularized reconstruction
T Sarwar, C Yaras, X Li, Q Qu, PC Ku
Nano Letters 22 (20), 8174-8180, 2022
92022
Invariant Low-Dimensional Subspaces in Gradient Descent for Learning Deep Matrix Factorizations
C Yaras, P Wang, W Hu, Z Zhu, L Balzano, Q Qu
NeurIPS 2023 Workshop on Mathematics of Modern Machine Learning, 2023
52023
Accelerating Deep Learning in Reconstructive Spectroscopy Using Synthetic Data
P Li, C Yaras, T Sarwar, PC Ku, Q Qu
CLEO: Applications and Technology, JTu2A. 71, 2023
32023
系统目前无法执行此操作,请稍后再试。
文章 1–9