activity
20172022
most citedUnderstanding and Improving Transformer From a Multi-Particle Dynamic System Point of View

117 citations · 207 across the 12 of their papers we have counts for

collaborators
Showing cs.LGShow all

9 papers · 1 filter

cs.LG2022

Trained Model in Supervised Deep Learning is a Conditional Risk Minimizer

Yutong Xie, Dufan Wu, Bin Dong +1

We proved that a trained model in supervised deep learning minimizes the conditional risk for each input (Theorem 2.1). This property provided insights into the behavior of trained…

cs.LG202112 cited

Solving Partial Differential Equations with Point Source Based on Physics-Informed Neural Networks

Xiang Huang, Hongsheng Liu, Beiji Shi +11

In recent years, deep learning technology has been used to solve partial differential equations (PDEs), among which the physics-informed neural networks (PINNs) emerges to be a pro…

cs.LG2020

A Practical Layer-Parallel Training Algorithm for Residual Networks

Qi Sun, Hexin Dong, Zewei Chen +5

Gradient-based algorithms for training ResNets typically require a forward pass of the input data, followed by back-propagating the objective gradient to update parameters, which a…

cs.LG20206 cited

Transferred Discrepancy: Quantifying the Difference Between Representations

Yunzhen Feng, Runtian Zhai, Di He +2

Understanding what information neural networks capture is an essential problem in deep learning, and studying whether different models capture similar features is an initial step t…

cs.LG2020

Enhancing Certified Robustness via Smoothed Weighted Ensembling

Chizhou Liu, Yunzhen Feng, Ranran Wang +1

Randomized smoothing has achieved state-of-the-art certified robustness against -norm adversarial attacks. However, it is not wholly resolved on how to find the optimal base c…

cs.LG20202 cited

Blind Adversarial Training: Balance Accuracy and Robustness

Haidong Xie, Xueshuang Xiang, Naijin Liu +1

Adversarial training (AT) aims to improve the robustness of deep learning models by mixing clean data and adversarial examples (AEs). Most existing AT approaches can be grouped int…