13 citations · 43 across the 10 of their papers we have counts for
10 papers
Dependence Induced Representations
Xiangxiang Xu, Lizhong Zheng
We study the problem of learning feature representations from a pair of random variables, where we focus on the representations that are induced by their dependence. We provide suf…
Operator SVD with Neural Networks via Nested Low-Rank Approximation
J. Jon Ryu, Xiangxiang Xu, H. S. Melihcan Erol +3
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 scien…
Neural Feature Learning in Function Space
Xiangxiang Xu, Lizhong Zheng
We present a novel framework for learning system design with neural feature extractors. First, we introduce the feature geometry, which unifies statistical dependence and feature r…
Kernel Subspace and Feature Extraction
Xiangxiang Xu, Lizhong Zheng
We study kernel methods in machine learning from the perspective of feature subspace. We establish a one-to-one correspondence between feature subspaces and kernels and propose an…
On Distributed Learning with Constant Communication Bits
Xiangxiang Xu, Shao-Lun Huang
In this paper, we study a distributed learning problem constrained by constant communication bits. Specifically, we consider the distributed hypothesis testing (DHT) problem where…
Maximum Likelihood Estimation for Multimodal Learning with Missing Modality
Fei Ma, Xiangxiang Xu, Shao-Lun Huang +1
Multimodal learning has achieved great successes in many scenarios. Compared with unimodal learning, it can effectively combine the information from different modalities to improve…
An Information-theoretic Approach to Unsupervised Feature Selection for High-Dimensional Data
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. The…
On the Sample Complexity of HGR Maximal Correlation Functions for Large Datasets
Shao-Lun Huang, Xiangxiang Xu
The Hirschfeld-Gebelein-Rényi (HGR) maximal correlation and the corresponding functions have been shown useful in many machine learning scenarios. In this paper, we study the sampl…
An Information Theoretic Interpretation to Deep Neural Networks
Shao-Lun Huang, Xiangxiang Xu, Lizhong Zheng +1
It is commonly believed that the hidden layers of deep neural networks (DNNs) attempt to extract informative features for learning tasks. In this paper, we formalize this intuition…
An Efficient Approach to Informative Feature Extraction from Multimodal Data
Lichen Wang, Jiaxiang Wu, Shao-Lun Huang +4
One primary focus in multimodal feature extraction is to find the representations of individual modalities that are maximally correlated. As a well-known measure of dependence, the…