65 citations · 152 across the 20 of their papers we have counts for
20 papers
Understanding Latent Diffusability via Fisher Geometry
Jing Gu, Morteza Mardani, Wonjun Lee +2
Diffusion models often degrade in latent spaces, yet the formal causes remain poorly understood. We quantify latent-space diffusability via the rate of change of the Minimum Mean S…
Stein Discrepancy for Unsupervised Domain Adaptation
Anneke von Seeger, Dongmian Zou, Gilad Lerman
Unsupervised domain adaptation (UDA) aims to improve model performance on an unlabeled target domain using a related, labeled source domain. A common approach aligns source and tar…
Geometry-Preserving Encoder/Decoder in Latent Generative Models
Wonjun Lee, Riley C. W. O'Neill, Dongmian Zou +2
Generative modeling aims to generate new data samples that resemble a given dataset. When using diffusion models for this task, one of the main challenges is solving the problem in…
Improving Hyperbolic Representations via Gromov-Wasserstein Regularization
Yifei Yang, Wonjun Lee, Dongmian Zou +1
Hyperbolic representations have shown remarkable efficacy in modeling inherent hierarchies and complexities within data structures. Hyperbolic neural networks have been commonly ap…
Monotone Generative Modeling via a Gromov-Monge Embedding
Wonjun Lee, Yifei Yang, Dongmian Zou +1
Generative adversarial networks (GANs) are popular for generative tasks; however, they often require careful architecture selection, extensive empirical tuning, and are prone to mo…
Hyperbolic Convolution via Kernel Point Aggregation
Eric Qu, Dongmian Zou
Learning representations according to the underlying geometry is of vital importance for non-Euclidean data. Studies have revealed that the hyperbolic space can effectively embed h…
Graph Neural Network Based Node Deployment for Throughput Enhancement
Yifei Yang, Dongmian Zou, Xiaofan He
The recent rapid growth in mobile data traffic entails a pressing demand for improving the throughput of the underlying wireless communication networks. Network node deployment has…
An Unpooling Layer for Graph Generation
Yinglong Guo, Dongmian Zou, Gilad Lerman
We propose a novel and trainable graph unpooling layer for effective graph generation. Given a graph with features, the unpooling layer enlarges this graph and learns its desired n…
Robust Vector Quantized-Variational Autoencoder
Chieh-Hsin Lai, Dongmian Zou, Gilad Lerman
Image generative models can learn the distributions of the training data and consequently generate examples by sampling from these distributions. However, when the training dataset…
Autoencoding Hyperbolic Representation for Adversarial Generation
Eric Qu, Dongmian Zou
With the recent advance of geometric deep learning, neural networks have been extensively used for data in non-Euclidean domains. In particular, hyperbolic neural networks have pro…
Ensemble Riemannian Data Assimilation over the Wasserstein Space
Sagar K. Tamang, Ardeshir Ebtehaj, Peter J. Van Leeuwen +2
In this paper, we present an ensemble data assimilation paradigm over a Riemannian manifold equipped with the Wasserstein metric. Unlike the Eulerian penalization of error in the E…
Novelty Detection via Robust Variational Autoencoding
Chieh-Hsin Lai, Dongmian Zou, Gilad Lerman
We propose a new method for novelty detection that can tolerate high corruption of the training points, whereas previous works assumed either no or very low corruption. Our method…
Regularized Variational Data Assimilation for Bias Treatment using the Wasserstein Metric
Sagar K. Tamang, Ardeshir Ebtehaj, Dongmian Zou +1
This paper presents a new variational data assimilation (VDA) approach for the formal treatment of bias in both model outputs and observations. This approach relies on the Wasserst…
Robust Subspace Recovery Layer for Unsupervised Anomaly Detection
Chieh-Hsin Lai, Dongmian Zou, Gilad Lerman
We propose a neural network for unsupervised anomaly detection with a novel robust subspace recovery layer (RSR layer). This layer seeks to extract the underlying subspace from a l…
Encoding Robust Representation for Graph Generation
Dongmian Zou, Gilad Lerman
Generative networks have made it possible to generate meaningful signals such as images and texts from simple noise. Recently, generative methods based on GAN and VAE were develope…
On Lipschitz Bounds of General Convolutional Neural Networks
Dongmian Zou, Radu Balan, Maneesh Singh
Many convolutional neural networks (CNNs) have a feed-forward structure. In this paper, a linear program that estimates the Lipschitz bound of such CNNs is proposed. Several CNNs,…
Graph Convolutional Neural Networks via Scattering
Dongmian Zou, Gilad Lerman
We generalize the scattering transform to graphs and consequently construct a convolutional neural network on graphs. We show that under certain conditions, any feature generated b…
Lipschitz Properties for Deep Convolutional Networks
Radu Balan, Maneesh Singh, Dongmian Zou
In this paper we discuss the stability properties of convolutional neural networks. Convolutional neural networks are widely used in machine learning. In classification they are ma…
On Lipschitz Analysis and Lipschitz Synthesis for the Phase Retrieval Problem
Radu Balan, Dongmian Zou
In this paper we prove two results regarding reconstruction from magnitudes of frame coefficients (the so called "phase retrieval problem"). First we show that phase retrievability…
Phase Retrieval using Lipschitz Continuous Maps
Radu Balan, Dongmian Zou
In this note we prove that reconstruction from magnitudes of frame coefficients (the so called "phase retrieval problem") can be performed using Lipschitz continuous maps. Specific…