1 code implementation • 6 Feb 2024 • J. Jon Ryu, Xiangxiang Xu, H. S. Melihcan Erol, Yuheng Bu, Lizhong Zheng, Gregory W. Wornell
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 scientific computing problems.
1 code implementation • 18 Sep 2023 • Xiangxiang Xu, Lizhong Zheng
We present a novel framework for learning system design based on neural feature extractors.
no code implementations • 4 Jan 2023 • Xiangxiang Xu, Lizhong Zheng
We study kernel methods in machine learning from the perspective of feature subspace.
no code implementations • NeurIPS 2021 • Xinyi Tong, Xiangxiang Xu, Shao-Lun Huang, Lizhong Zheng
Current transfer learning algorithm designs mainly focus on the similarities between source and target tasks, while the impacts of the sample sizes of these tasks are often not sufficiently addressed.
no code implementations • 14 Sep 2021 • Xiangxiang Xu, Shao-Lun Huang
Specifically, we consider the distributed hypothesis testing (DHT) problem where two distributed nodes are constrained to transmit a constant number of bits to a central decoder.
no code implementations • 24 Aug 2021 • Fei Ma, Xiangxiang Xu, Shao-Lun Huang, Lin Zhang
Moreover, we develop a generalized form of the softmax function to effectively implement maximum likelihood estimation in an end-to-end manner.
no code implementations • 8 Oct 2019 • Shao-Lun Huang, Xiangxiang Xu, Lizhong Zheng
In this paper, we propose an information-theoretic approach to design the functional representations to extract the hidden common structure shared by a set of random variables.
no code implementations • 16 May 2019 • Shao-Lun Huang, Xiangxiang Xu, Lizhong Zheng, Gregory W. Wornell
It is commonly believed that the hidden layers of deep neural networks (DNNs) attempt to extract informative features for learning tasks.
no code implementations • 22 Nov 2018 • Lichen Wang, Jiaxiang Wu, Shao-Lun Huang, Lizhong Zheng, Xiangxiang Xu, Lin Zhang, Junzhou Huang
We further generalize the framework to handle more than two modalities and missing modalities.