On universal features for high-dimensional learning and inference

SL Huang, A Makur, GW Wornell, L Zheng - arXiv preprint arXiv …, 2019 - arxiv.org
We consider the problem of identifying universal low-dimensional features from high-
dimensional data for inference tasks in settings involving learning. For such problems, we …

[PDF][PDF] A geometric framework for neural feature learning

X Xu, L Zheng - arXiv preprint arXiv:2309.10140, 2023 - researchgate.net
We present a novel framework for learning system design based on neural feature
extractors. First, we introduce the feature geometry, which unifies statistical dependence and …

Identifying the technological position of semiconductor laser developers: a patent-based analytical perspective

SH Chang - International Journal of Innovation Science, 2023 - emerald.com
Purpose Defining and validating a map of related technologies is critical for managers,
investors and inventors. Because of the increase in the applications of and demand for …

Operator SVD with Neural Networks via Nested Low-Rank Approximation

JJ Ryu, X Xu, HS Erol, Y Bu, L Zheng… - arXiv preprint arXiv …, 2024 - arxiv.org
Computing eigenvalue decomposition (EVD) of a given linear operator, or finding its leading
eigenvalues and eigenfunctions, is a fundamental task in many machine learning and …

[引用][C] Air-quality Sensors: Patent Portfolio and Technology Development

SH Chang, FY Yeh