
DeepParticle: learning invariant measure by a deep neural network minimizing Wasserstein distance on data generated from an interacting particle method
We introduce the so called DeepParticle method to learn and generate inv...
read it

Convergence analysis of a Lagrangian numerical scheme in computing effective diffusivity of 3D timedependent flows
In this paper, we study the convergence analysis for a robust stochastic...
read it

A convergent interacting particle method and computation of KPP front speeds in chaotic flows
In this paper, we study the propagation speeds of reactiondiffusionadv...
read it

A SemiLagrangian Computation of Front Speeds of Gequation in ABC and Kolmogorov Flows with Estimation via Ballistic Orbits
The ArnoldBeltramiChildress (ABC) flow and the Kolmogorov flow are thr...
read it

Recurrence of Optimum for Training Weight and Activation Quantized Networks
Deep neural networks (DNNs) are quantized for efficient inference on res...
read it

Learning Quantized Neural Nets by Coarse Gradient Method for Nonlinear Classification
Quantized or lowbit neural networks are attractive due to their inferen...
read it

A SpatialTemporal Graph Based Hybrid Infectious Disease Model with Application to COVID19
As the COVID19 pandemic evolves, reliable prediction plays an important...
read it

Nonconvex Regularization for Network Slimming:Compressing CNNs Even More
In the last decade, convolutional neural networks (CNNs) have evolved to...
read it

Lorentzian Peak Sharpening and Sparse Blind Source Separation for NMR Spectroscopy
In this paper, we introduce a preprocessing technique for blind source s...
read it

An Integrated Approach to Produce Robust Models with High Efficiency
Deep Neural Networks (DNNs) needs to be both efficient and robust for pr...
read it

RARTS: a Relaxed Architecture Search Method
Differentiable architecture search (DARTS) is an effective method for da...
read it

A Recurrent Neural Network and Differential Equation Based Spatiotemporal Infectious Disease Model with Application to COVID19
The outbreaks of Coronavirus Disease 2019 (COVID19) have impacted the w...
read it

A Weighted Difference of Anisotropic and Isotropic Total Variation for Relaxed MumfordShah Color and Multiphase Image Segmentation
In a class of piecewiseconstant image segmentation models, we incorpora...
read it

Global Convergence and Geometric Characterization of Slow to Fast Weight Evolution in Neural Network Training for Classifying Linearly NonSeparable Data
In this paper, we study the dynamics of gradient descent in learning neu...
read it

ℓ_0 Regularized Structured Sparsity Convolutional Neural Networks
Deepening and widening convolutional neural networks (CNNs) significantl...
read it

Computing Residual Diffusivity by Adaptive Basis Learning via SuperResolution Deep Neural Networks
It is expensive to compute residual diffusivity in chaotic incompressib...
read it

TwoGrid based Adaptive Proper Orthogonal Decomposition Algorithm for Time Dependent Partial Differential Equations
In this article, we propose a twogrid based adaptive proper orthogonal ...
read it

Convergence of stochastic structurepreserving schemes for computing effective diffusivity in random flows
In this paper, we propose stochastic structurepreserving schemes to com...
read it

Understanding StraightThrough Estimator in Training Activation Quantized Neural Nets
Training activation quantized neural networks involves minimizing a piec...
read it

Learning Sparse Neural Networks via ℓ_0 and Tℓ_1 by a Relaxed Variable Splitting Method with Application to Multiscale Curve Classification
We study sparsification of convolutional neural networks (CNN) by a rela...
read it

A Study on GraphStructured Recurrent Neural Networks and Sparsification with Application to Epidemic Forecasting
We study epidemic forecasting on realworld health data by a graphstruc...
read it

AutoShuffleNet: Learning Permutation Matrices via an Exact Lipschitz Continuous Penalty in Deep Convolutional Neural Networks
ShuffleNet is a stateoftheart light weight convolutional neural netwo...
read it

Blended Coarse Gradient Descent for Full Quantization of Deep Neural Networks
Quantized deep neural networks (QDNNs) are attractive due to their much ...
read it

BinaryRelax: A Relaxation Approach For Training Deep Neural Networks With Quantized Weights
We propose BinaryRelax, a simple twophase algorithm, for training deep ...
read it

Deep Learning for RealTime Crime Forecasting and its Ternarization
Realtime crime forecasting is important. However, accurate prediction o...
read it

A Method for Finding Structured Sparse Solutions to Nonnegative Least Squares Problems with Applications
Demixing problems in many areas such as hyperspectral imaging and differ...
read it

A convex model for nonnegative matrix factorization and dimensionality reduction on physical space
A collaborative convex framework for factoring a data matrix X into a no...
read it
Jack Xin
is this you? claim profile