b'Zhanxing Zhu'

research

∙ 03/31/2021

Positive-Negative Momentum: Manipulating Stochastic Gradient Noise to Improve Generalization

It is well-known that stochastic gradient noise (SGN) acts as implicit r...

Zeke Xie, et al. ∙

research

∙ 12/15/2020

Amata: An Annealing Mechanism for Adversarial Training Acceleration

Despite the empirical success in various domains, it has been revealed t...

Nanyang Ye, et al. ∙

research

∙ 10/20/2020

Knowledge Distillation in Wide Neural Networks: Risk Bound, Data Efficiency and Imperfect Teacher

Knowledge distillation is a strategy of training a student network with ...

Guangda Ji, et al. ∙

research

∙ 10/20/2020

Neural Approximate Sufficient Statistics for Implicit Models

We consider the fundamental problem of how to automatically construct su...

Yanzhi Chen, et al. ∙

research

∙ 08/10/2020

Informative Dropout for Robust Representation Learning: A Shape-bias Perspective

Convolutional Neural Networks (CNNs) are known to rely more on local tex...

Baifeng Shi, et al. ∙

research

∙ 06/15/2020

Spherical Motion Dynamics of Deep Neural Networks with Batch Normalization and Weight Decay

We comprehensively reveal the learning dynamics of deep neural networks ...

Ruosi Wan, et al. ∙

research

∙ 06/14/2020

Classify and Generate Reciprocally: Simultaneous Positive-Unlabelled Learning and Conditional Generation with Extra Data

The scarcity of class-labeled data is a ubiquitous bottleneck in a wide ...

Bing Yu, et al. ∙

research

∙ 06/08/2020

Global Robustness Verification Networks

The wide deployment of deep neural networks, though achieving great succ...

Weidi Sun, et al. ∙

research

∙ 02/21/2020

Black-Box Certification with Randomized Smoothing: A Functional Optimization Based Framework

Randomized classifiers have been shown to provide a promising approach f...

Dinghuai Zhang, et al. ∙

research

∙ 11/21/2019

Patch-level Neighborhood Interpolation: A General and Effective Graph-based Regularization Strategy

Regularization plays a crucial role in machine learning models, especial...

Ke Sun, et al. ∙

research

∙ 11/18/2019

Towards Making Deep Transfer Learning Never Hurt

Transfer learning have been frequently used to improve deep neural netwo...

Ruosi Wan, et al. ∙

research

∙ 08/20/2019

Spatio-temporal Manifold Learning for Human Motions via Long-horizon Modeling

Data-driven modeling of human motions is ubiquitous in computer graphics...

Edmond S. L. Ho, et al. ∙

research

∙ 08/14/2019

AdaGCN: Adaboosting Graph Convolutional Networks into Deep Models

The design of deep graph models still remains to be investigated and the...

Ke Sun, et al. ∙

research

∙ 06/18/2019

The Multiplicative Noise in Stochastic Gradient Descent: Data-Dependent Regularization, Continuous and Discrete Approximation

The randomness in Stochastic Gradient Descent (SGD) is considered to pla...

Jingfeng Wu, et al. ∙

research

∙ 05/30/2019

Differentiable Neural Architecture Search via Proximal Iterations

Neural architecture search (NAS) recently attracts much research attenti...

Quanming Yao, et al. ∙

research

∙ 05/24/2019

On the Learning Dynamics of Two-layer Nonlinear Convolutional Neural Networks

Convolutional neural networks (CNNs) have achieved remarkable performanc...

Bing Yu, et al. ∙

research

∙ 05/23/2019

Interpreting Adversarially Trained Convolutional Neural Networks

We attempt to interpret how adversarially trained convolutional neural n...

Tianyuan Zhang, et al. ∙

research

∙ 05/10/2019

Bayesian Optimized Continual Learning with Attention Mechanism

Though neural networks have achieved much progress in various applicatio...

Ju Xu, et al. ∙

research

∙ 05/02/2019

You Only Propagate Once: Accelerating Adversarial Training Using Maximal Principle

Deep learning achieves state-of-the-art results in many areas. However r...

Dinghuai Zhang, et al. ∙

research

∙ 05/02/2019

You Only Propagate Once: Painless Adversarial Training Using Maximal Principle

Deep learning achieves state-of-the-art results in many areas. However r...

Dinghuai Zhang, et al. ∙

research

∙ 03/13/2019

ST-UNet: A Spatio-Temporal U-Network for Graph-structured Time Series Modeling

The spatio-temporal graph learning is becoming an increasingly important...

Bing Yu, et al. ∙

research

∙ 03/03/2019

3D Graph Convolutional Networks with Temporal Graphs: A Spatial Information Free Framework For Traffic Forecasting

Spatio-temporal prediction plays an important role in many application a...

Bing Yu, et al. ∙

research

∙ 02/28/2019

Virtual Adversarial Training on Graph Convolutional Networks in Node Classification

The effectiveness of Graph Convolutional Networks (GCNs) has been demons...

Ke Sun, et al. ∙

research

∙ 02/28/2019

Multi-Stage Self-Supervised Learning for Graph Convolutional Networks

Graph Convolutional Networks(GCNs) play a crucial role in graph learning...

Ke Sun, et al. ∙

research

∙ 02/28/2019

Enhancing the Robustness of Deep Neural Networks by Boundary Conditional GAN

Deep neural networks have been widely deployed in various machine learni...

Ke Sun, et al. ∙

research

∙ 02/28/2019

Towards Understanding Adversarial Examples Systematically: Exploring Data Size, Task and Model Factors

Most previous works usually explained adversarial examples from several ...

Ke Sun, et al. ∙

research

∙ 01/18/2019

Quasi-potential as an implicit regularizer for the loss function in the stochastic gradient descent

We interpret the variational inference of the Stochastic Gradient Descen...

Wenqing Hu, et al. ∙

research

∙ 08/18/2018

Tangent-Normal Adversarial Regularization for Semi-supervised Learning

The ever-increasing size of modern datasets combined with the difficulty...

Bing Yu, et al. ∙

research

∙ 06/01/2018

Neural Control Variates for Variance Reduction

In statistics and machine learning, approximation of an intractable inte...

Zhanxing Zhu, et al. ∙

research

∙ 05/31/2018

Reinforced Continual Learning

Most artificial intelligence models have limiting ability to solve new t...

Ju Xu, et al. ∙

research

∙ 03/01/2018

The Regularization Effects of Anisotropic Noise in Stochastic Gradient Descent

Understanding the generalization of deep learning has raised lots of con...

Zhanxing Zhu, et al. ∙

research

∙ 02/27/2018

Understanding and Enhancing the Transferability of Adversarial Examples

State-of-the-art deep neural networks are known to be vulnerable to adve...

Lei Wu, et al. ∙

research

∙ 09/14/2017

Spatio-temporal Graph Convolutional Neural Network: A Deep Learning Framework for Traffic Forecasting

The goal of traffic forecasting is to predict the future vital indicator...

Bing Yu, et al. ∙

research

∙ 06/30/2017

Towards Understanding Generalization of Deep Learning: Perspective of Loss Landscapes

It is widely observed that deep learning models with learned parameters ...

Lei Wu, et al. ∙

research

∙ 05/11/2017

Learning with Noise: Enhance Distantly Supervised Relation Extraction with Dynamic Transition Matrix

Distant supervision significantly reduces human efforts in building trai...

Bingfeng Luo, et al. ∙

research

∙ 03/13/2017

Langevin Dynamics with Continuous Tempering for Training Deep Neural Networks

Minimizing non-convex and high-dimensional objective functions is challe...

Nanyang Ye, et al. ∙

research

∙ 11/23/2015

Stochastic Parallel Block Coordinate Descent for Large-scale Saddle Point Problems

We consider convex-concave saddle point problems with a separable struct...

Zhanxing Zhu, et al. ∙

research

∙ 10/29/2015

Covariance-Controlled Adaptive Langevin Thermostat for Large-Scale Bayesian Sampling

Monte Carlo sampling for Bayesian posterior inference is a common approa...

Xiaocheng Shang, et al. ∙

research

∙ 06/12/2015

Adaptive Stochastic Primal-Dual Coordinate Descent for Separable Saddle Point Problems

We consider a generic convex-concave saddle point problem with separable...

Zhanxing Zhu, et al. ∙

Zhanxing Zhu

Featured Co-authors