activity
20032023
most citedMaximum bound principles for a class of semilinear parabolic equations and exponential time differencing schemes

12 citations · 27 across the 12 of their papers we have counts for

collaborators
Showing 2018Show all

6 papers · 1 filter

cs.LG2018

Stochastic Training of Residual Networks: a Differential Equation Viewpoint

Qi Sun, Yunzhe Tao, Qiang Du

During the last few years, significant attention has been paid to the stochastic training of artificial neural networks, which is known as an effective regularization approach that…

math.AP2018

Stochastic representation of solution to nonlocal-in-time diffusion

Qiang Du, Lorenzo Toniazzi, Zhi Zhou

The aim of this paper is to give a stochastic representation for the solution to a natural extension of the Caputo-type evolution equation. The nonlocal-in-time operator is defined…

cs.LG2018

Hierarchical Attention-Based Recurrent Highway Networks for Time Series Prediction

Yunzhe Tao, Lin Ma, Weizhong Zhang +3

Time series prediction has been studied in a variety of domains. However, it is still challenging to predict future series given historical observations and past exogenous data. Ex…

cs.LG2018

Nonlocal Neural Networks, Nonlocal Diffusion and Nonlocal Modeling

Yunzhe Tao, Qi Sun, Qiang Du +1

Nonlocal neural networks have been proposed and shown to be effective in several computer vision tasks, where the nonlocal operations can directly capture long-range dependencies i…

math.NA2018

Mathematics of Smoothed Particle Hydrodynamics: a Study via Nonlocal Stokes Equations

Qiang Du, Xiaochuan Tian

Smoothed Particle Hydrodynamics (SPH) is a popular numerical technique developed for simulating complex fluid flows. Among its key ingredients is the use of nonlocal integral relax…

cs.CL2018

A Reinforced Topic-Aware Convolutional Sequence-to-Sequence Model for Abstractive Text Summarization

Li Wang, Junlin Yao, Yunzhe Tao +3

In this paper, we propose a deep learning approach to tackle the automatic summarization tasks by incorporating topic information into the convolutional sequence-to-sequence (ConvS…