Alert button
Picture for Ruoyu Sun

Ruoyu Sun

Alert button

Invariant Layers for Graphs with Nodes of Different Types

Feb 27, 2023
Dmitry Rybin, Ruoyu Sun, Zhi-Quan Luo

Figure 1 for Invariant Layers for Graphs with Nodes of Different Types
Figure 2 for Invariant Layers for Graphs with Nodes of Different Types
Figure 3 for Invariant Layers for Graphs with Nodes of Different Types
Figure 4 for Invariant Layers for Graphs with Nodes of Different Types
Viaarxiv icon

Adversarial Rademacher Complexity of Deep Neural Networks

Nov 27, 2022
Jiancong Xiao, Yanbo Fan, Ruoyu Sun, Zhi-Quan Luo

Figure 1 for Adversarial Rademacher Complexity of Deep Neural Networks
Figure 2 for Adversarial Rademacher Complexity of Deep Neural Networks
Figure 3 for Adversarial Rademacher Complexity of Deep Neural Networks
Figure 4 for Adversarial Rademacher Complexity of Deep Neural Networks
Viaarxiv icon

DigGAN: Discriminator gradIent Gap Regularization for GAN Training with Limited Data

Nov 27, 2022
Tiantian Fang, Ruoyu Sun, Alex Schwing

Figure 1 for DigGAN: Discriminator gradIent Gap Regularization for GAN Training with Limited Data
Figure 2 for DigGAN: Discriminator gradIent Gap Regularization for GAN Training with Limited Data
Figure 3 for DigGAN: Discriminator gradIent Gap Regularization for GAN Training with Limited Data
Figure 4 for DigGAN: Discriminator gradIent Gap Regularization for GAN Training with Limited Data
Viaarxiv icon

Stability Analysis and Generalization Bounds of Adversarial Training

Oct 03, 2022
Jiancong Xiao, Yanbo Fan, Ruoyu Sun, Jue Wang, Zhi-Quan Luo

Figure 1 for Stability Analysis and Generalization Bounds of Adversarial Training
Figure 2 for Stability Analysis and Generalization Bounds of Adversarial Training
Figure 3 for Stability Analysis and Generalization Bounds of Adversarial Training
Figure 4 for Stability Analysis and Generalization Bounds of Adversarial Training
Viaarxiv icon

Adam Can Converge Without Any Modification on Update Rules

Aug 23, 2022
Yushun Zhang, Congliang Chen, Naichen Shi, Ruoyu Sun, Zhi-Quan Luo

Figure 1 for Adam Can Converge Without Any Modification on Update Rules
Figure 2 for Adam Can Converge Without Any Modification on Update Rules
Figure 3 for Adam Can Converge Without Any Modification on Update Rules
Figure 4 for Adam Can Converge Without Any Modification on Update Rules
Viaarxiv icon

Global Convergence of MAML and Theory-Inspired Neural Architecture Search for Few-Shot Learning

Mar 17, 2022
Haoxiang Wang, Yite Wang, Ruoyu Sun, Bo Li

Figure 1 for Global Convergence of MAML and Theory-Inspired Neural Architecture Search for Few-Shot Learning
Figure 2 for Global Convergence of MAML and Theory-Inspired Neural Architecture Search for Few-Shot Learning
Figure 3 for Global Convergence of MAML and Theory-Inspired Neural Architecture Search for Few-Shot Learning
Figure 4 for Global Convergence of MAML and Theory-Inspired Neural Architecture Search for Few-Shot Learning
Viaarxiv icon

Towards Understanding the Impact of Model Size on Differential Private Classification

Nov 27, 2021
Yinchen Shen, Zhiguo Wang, Ruoyu Sun, Xiaojing Shen

Figure 1 for Towards Understanding the Impact of Model Size on Differential Private Classification
Figure 2 for Towards Understanding the Impact of Model Size on Differential Private Classification
Figure 3 for Towards Understanding the Impact of Model Size on Differential Private Classification
Figure 4 for Towards Understanding the Impact of Model Size on Differential Private Classification
Viaarxiv icon

Federated Semi-Supervised Learning with Class Distribution Mismatch

Oct 29, 2021
Zhiguo Wang, Xintong Wang, Ruoyu Sun, Tsung-Hui Chang

Figure 1 for Federated Semi-Supervised Learning with Class Distribution Mismatch
Figure 2 for Federated Semi-Supervised Learning with Class Distribution Mismatch
Figure 3 for Federated Semi-Supervised Learning with Class Distribution Mismatch
Figure 4 for Federated Semi-Supervised Learning with Class Distribution Mismatch
Viaarxiv icon

Momentum Doesn't Change the Implicit Bias

Oct 08, 2021
Bohan Wang, Qi Meng, Huishuai Zhang, Ruoyu Sun, Wei Chen, Zhi-Ming Ma

Figure 1 for Momentum Doesn't Change the Implicit Bias
Figure 2 for Momentum Doesn't Change the Implicit Bias
Figure 3 for Momentum Doesn't Change the Implicit Bias
Figure 4 for Momentum Doesn't Change the Implicit Bias
Viaarxiv icon

Achieving Small Test Error in Mildly Overparameterized Neural Networks

Apr 24, 2021
Shiyu Liang, Ruoyu Sun, R. Srikant

Viaarxiv icon