
Kernel MMD TwoSample Tests for Manifold Data
We present a study of kernel MMD twosample test statistics in the manif...
read it

Convergence of Gaussiansmoothed optimal transport distance with subgamma distributions and dependent samples
The Gaussiansmoothed optimal transport (GOT) framework, recently propos...
read it

Eigenconvergence of Gaussian kernelized graph Laplacian by manifold heat interpolation
This work studies the spectral convergence of graph Laplacian to the Lap...
read it

Convergence of Graph Laplacian with kNN Selftuned Kernels
Kernelized Gram matrix W constructed from data points {x_i}_i=1^N as W_i...
read it

ACDC: Weight Sharing in AtomCoefficient Decomposed Convolution
Convolutional Neural Networks (CNNs) are known to be significantly over...
read it

Graph Neural Networks with Lowrank Learnable Local Filters
For the classification of graph data consisting of features sampled on a...
read it

ButterflyNet2: Simplified ButterflyNet and Fourier Transform Initialization
Structured CNN designed using the prior information of problems potentia...
read it

Classification Logit Twosample Testing by Neural Networks
The recent success of generative adversarial networks and variational le...
read it

Stochastic Conditional Generative Networks with Basis Decomposition
While generative adversarial networks (GANs) have revolutionized machine...
read it

Domaininvariant Learning using Adaptive Filter Decomposition
Domain shifts are frequently encountered in realworld scenarios. In thi...
read it

ScaleEquivariant Neural Networks with Decomposed Convolutional Filters
Encoding the input scale information explicitly into the representation ...
read it

Spectral Embedding Norm: Looking Deep into the Spectrum of the Graph Laplacian
The extraction of clusters from a dataset which includes multiple cluste...
read it

ButterflyNet: Optimal Function Representation Based on Convolutional Neural Networks
Deep networks, especially Convolutional Neural Networks (CNNs), have bee...
read it

RotDCF: Decomposition of Convolutional Filters for RotationEquivariant Deep Networks
Explicit encoding of group actions in deep features makes it possible fo...
read it

Defending against Adversarial Images using Basis Functions Transformations
We study the effectiveness of various approaches that defend against adv...
read it

DCFNet: Deep Neural Network with Decomposed Convolutional Filters
Filters in a Convolutional Neural Network (CNN) contain model parameters...
read it

Twosample Statistics Based on Anisotropic Kernels
The paper introduces a new kernelbased Maximum Mean Discrepancy (MMD) s...
read it

The Geometry of Nodal Sets and Outlier Detection
Let (M,g) be a compact manifold and let Δϕ_k = λ_k ϕ_k be the sequence ...
read it

Provable Estimation of the Number of Blocks in Block Models
Community detection is a fundamental unsupervised learning problem for u...
read it

On the Diffusion Geometry of Graph Laplacians and Applications
We study directed, weighted graphs G=(V,E) and consider the (not necessa...
read it

A Deep Learning Approach to Unsupervised Ensemble Learning
We show how deep learning methods can be applied in the context of crowd...
read it

Unsupervised Deep Haar Scattering on Graphs
The classification of highdimensional data defined on graphs is particu...
read it
Xiuyuan Cheng
is this you? claim profile