45 citations · 273 across the 45 of their papers we have counts for
45 papers
Neural Differential Recurrent Neural Network with Adaptive Time Steps
Yixuan Tan, Liyan Xie, Xiuyuan Cheng
The neural Ordinary Differential Equation (ODE) model has shown success in learning complex continuous-time processes from observations on discrete time stamps. In this work, we co…
Deep graph kernel point processes over networks
Zheng Dong, Matthew Repasky, Xiuyuan Cheng +1
Point process models are widely used for continuous-time discrete-event data, where each data point includes time and additional information called "marks," such as locations, node…
G-invariant diffusion maps
Eitan Rosen, Xiuyuan Cheng, Yoel Shkolnisky
The diffusion maps embedding of data lying on a manifold has shown success in tasks such as dimensionality reduction, clustering, and data visualization. In this work, we consider…
Computing high-dimensional optimal transport by flow neural networks
Chen Xu, Xiuyuan Cheng, Yao Xie
Computing optimal transport (OT) for general high-dimensional data has been a long-standing challenge. Despite much progress, most of the efforts including neural network methods h…
The G-invariant graph Laplacian
Eitan Rosen, Paulina Hoyos, Xiuyuan Cheng +2
Graph Laplacian based algorithms for data lying on a manifold have been proven effective for tasks such as dimensionality reduction, clustering, and denoising. In this work, we con…
Normalizing flow neural networks by JKO scheme
Chen Xu, Xiuyuan Cheng, Yao Xie
Normalizing flow is a class of deep generative models for efficient sampling and likelihood estimation, which achieves attractive performance, particularly in high dimensions. The…
Spatio-temporal point processes with deep non-stationary kernels
Zheng Dong, Xiuyuan Cheng, Yao Xie
Point process data are becoming ubiquitous in modern applications, such as social networks, health care, and finance. Despite the powerful expressiveness of the popular recurrent n…
Neural network-based CUSUM for online change-point detection
Tingnan Gong, Junghwan Lee, Xiuyuan Cheng +1
Change-point detection, detecting an abrupt change in the data distribution from sequential data, is a fundamental problem in statistics and machine learning. CUSUM is a popular st…
Robust Inference of Manifold Density and Geometry by Doubly Stochastic Scaling
Boris Landa, Xiuyuan Cheng
The Gaussian kernel and its traditional normalizations (e.g., row-stochastic) are popular approaches for assessing similarities between data points. Yet, they can be inaccurate und…
Neural Stein critics with staged -regularization
Matthew Repasky, Xiuyuan Cheng, Yao Xie
Learning to differentiate model distributions from observed data is a fundamental problem in statistics and machine learning, and high-dimensional data remains a challenging settin…
SpecNet2: Orthogonalization-free spectral embedding by neural networks
Ziyu Chen, Yingzhou Li, Xiuyuan Cheng
Spectral methods which represent data points by eigenvectors of kernel matrices or graph Laplacian matrices have been a primary tool in unsupervised data analysis. In many applicat…
Bi-stochastically normalized graph Laplacian: convergence to manifold Laplacian and robustness to outlier noise
Xiuyuan Cheng, Boris Landa
Bi-stochastic normalization provides an alternative normalization of graph Laplacians in graph-based data analysis and can be computed efficiently by Sinkhorn-Knopp (SK) iterations…
Invertible Neural Networks for Graph Prediction
Chen Xu, Xiuyuan Cheng, Yao Xie
Graph prediction problems prevail in data analysis and machine learning. The inverse prediction problem, namely to infer input data from given output labels, is of emerging interes…
An alternative approach to train neural networks using monotone variational inequality
Chen Xu, Xiuyuan Cheng, Yao Xie
We propose an alternative approach to neural network training using the monotone vector field, an idea inspired by the seminal work of Juditsky and Nemirovski [Juditsky & Nemirovsk…
Crime Hot-Spot Modeling via Topic Modeling and Relative Density Estimation
Jonathan Zhou, Sarah Huestis-Mitchell, Xiuyuan Cheng +1
We present a method to capture groupings of similar calls and determine their relative spatial distribution from a collection of crime record narratives. We first obtain a topic di…
Neural Spectral Marked Point Processes
Shixiang Zhu, Haoyun Wang, Zheng Dong +2
Self- and mutually-exciting point processes are popular models in machine learning and statistics for dependent discrete event data. To date, most existing models assume stationary…
Neural Tangent Kernel Maximum Mean Discrepancy
Xiuyuan Cheng, Yao Xie
We present a novel neural network Maximum Mean Discrepancy (MMD) statistic by identifying a new connection between neural tangent kernel (NTK) and MMD. This connection enables us t…
Kernel Two-Sample Tests for Manifold Data
Xiuyuan Cheng, Yao Xie
We present a study of a kernel-based two-sample test statistic related to the Maximum Mean Discrepancy (MMD) in the manifold data setting, assuming that high-dimensional observatio…
Convergence of Gaussian-smoothed optimal transport distance with sub-gamma distributions and dependent samples
Yixing Zhang, Xiuyuan Cheng, Galen Reeves
The Gaussian-smoothed optimal transport (GOT) framework, recently proposed by Goldfeld et al., scales to high dimensions in estimation and provides an alternative to entropy regula…
Eigen-convergence of Gaussian kernelized graph Laplacian by manifold heat interpolation
Xiuyuan Cheng, Nan Wu
This work studies the spectral convergence of graph Laplacian to the Laplace-Beltrami operator when the graph affinity matrix is constructed from random samples on a -dimens…
Convergence of Graph Laplacian with kNN Self-tuned Kernels
Xiuyuan Cheng, Hau-Tieng Wu
Kernelized Gram matrix constructed from data points as is widely used in graph-based geometric data analysis…
ACDC: Weight Sharing in Atom-Coefficient Decomposed Convolution
Ze Wang, Xiuyuan Cheng, Guillermo Sapiro +1
Convolutional Neural Networks (CNNs) are known to be significantly over-parametrized, and difficult to interpret, train and adapt. In this paper, we introduce a structural regulari…
Graph Convolution with Low-rank Learnable Local Filters
Xiuyuan Cheng, Zichen Miao, Qiang Qiu
Geometric variations like rotation, scaling, and viewpoint changes pose a significant challenge to visual understanding. One common solution is to directly model certain intrinsic…
Butterfly-Net2: Simplified Butterfly-Net and Fourier Transform Initialization
Zhongshu Xu, Yingzhou Li, Xiuyuan Cheng
Structured CNN designed using the prior information of problems potentially improves efficiency over conventional CNNs in various tasks in solving PDEs and inverse problems in sign…