Alert button
Picture for Bao Wang

Bao Wang

Alert button

Adaptive and Implicit Regularization for Matrix Completion

Aug 11, 2022
Zhemin Li, Tao Sun, Hongxia Wang, Bao Wang

Figure 1 for Adaptive and Implicit Regularization for Matrix Completion
Figure 2 for Adaptive and Implicit Regularization for Matrix Completion
Figure 3 for Adaptive and Implicit Regularization for Matrix Completion
Figure 4 for Adaptive and Implicit Regularization for Matrix Completion
Viaarxiv icon

Momentum Transformer: Closing the Performance Gap Between Self-attention and Its Linearization

Aug 01, 2022
Tan Nguyen, Richard G. Baraniuk, Robert M. Kirby, Stanley J. Osher, Bao Wang

Figure 1 for Momentum Transformer: Closing the Performance Gap Between Self-attention and Its Linearization
Figure 2 for Momentum Transformer: Closing the Performance Gap Between Self-attention and Its Linearization
Figure 3 for Momentum Transformer: Closing the Performance Gap Between Self-attention and Its Linearization
Figure 4 for Momentum Transformer: Closing the Performance Gap Between Self-attention and Its Linearization
Viaarxiv icon

Proximal Implicit ODE Solvers for Accelerating Learning Neural ODEs

Apr 19, 2022
Justin Baker, Hedi Xia, Yiwei Wang, Elena Cherkaev, Akil Narayan, Long Chen, Jack Xin, Andrea L. Bertozzi, Stanley J. Osher, Bao Wang

Figure 1 for Proximal Implicit ODE Solvers for Accelerating Learning Neural ODEs
Figure 2 for Proximal Implicit ODE Solvers for Accelerating Learning Neural ODEs
Figure 3 for Proximal Implicit ODE Solvers for Accelerating Learning Neural ODEs
Figure 4 for Proximal Implicit ODE Solvers for Accelerating Learning Neural ODEs
Viaarxiv icon

Learning POD of Complex Dynamics Using Heavy-ball Neural ODEs

Feb 24, 2022
Justin Baker, Elena Cherkaev, Akil Narayan, Bao Wang

Figure 1 for Learning POD of Complex Dynamics Using Heavy-ball Neural ODEs
Figure 2 for Learning POD of Complex Dynamics Using Heavy-ball Neural ODEs
Figure 3 for Learning POD of Complex Dynamics Using Heavy-ball Neural ODEs
Figure 4 for Learning POD of Complex Dynamics Using Heavy-ball Neural ODEs
Viaarxiv icon

glassoformer: a query-sparse transformer for post-fault power grid voltage prediction

Jan 22, 2022
Yunling Zheng, Carson Hu, Guang Lin, Meng Yue, Bao Wang, Jack Xin

Figure 1 for glassoformer: a query-sparse transformer for post-fault power grid voltage prediction
Figure 2 for glassoformer: a query-sparse transformer for post-fault power grid voltage prediction
Figure 3 for glassoformer: a query-sparse transformer for post-fault power grid voltage prediction
Figure 4 for glassoformer: a query-sparse transformer for post-fault power grid voltage prediction
Viaarxiv icon

Efficient and Reliable Overlay Networks for Decentralized Federated Learning

Dec 12, 2021
Yifan Hua, Kevin Miller, Andrea L. Bertozzi, Chen Qian, Bao Wang

Figure 1 for Efficient and Reliable Overlay Networks for Decentralized Federated Learning
Figure 2 for Efficient and Reliable Overlay Networks for Decentralized Federated Learning
Figure 3 for Efficient and Reliable Overlay Networks for Decentralized Federated Learning
Figure 4 for Efficient and Reliable Overlay Networks for Decentralized Federated Learning
Viaarxiv icon

How Does Momentum Benefit Deep Neural Networks Architecture Design? A Few Case Studies

Oct 19, 2021
Bao Wang, Hedi Xia, Tan Nguyen, Stanley Osher

Figure 1 for How Does Momentum Benefit Deep Neural Networks Architecture Design? A Few Case Studies
Figure 2 for How Does Momentum Benefit Deep Neural Networks Architecture Design? A Few Case Studies
Figure 3 for How Does Momentum Benefit Deep Neural Networks Architecture Design? A Few Case Studies
Figure 4 for How Does Momentum Benefit Deep Neural Networks Architecture Design? A Few Case Studies
Viaarxiv icon

Training Deep Neural Networks with Adaptive Momentum Inspired by the Quadratic Optimization

Oct 18, 2021
Tao Sun, Huaming Ling, Zuoqiang Shi, Dongsheng Li, Bao Wang

Figure 1 for Training Deep Neural Networks with Adaptive Momentum Inspired by the Quadratic Optimization
Figure 2 for Training Deep Neural Networks with Adaptive Momentum Inspired by the Quadratic Optimization
Figure 3 for Training Deep Neural Networks with Adaptive Momentum Inspired by the Quadratic Optimization
Figure 4 for Training Deep Neural Networks with Adaptive Momentum Inspired by the Quadratic Optimization
Viaarxiv icon

Heavy Ball Neural Ordinary Differential Equations

Oct 10, 2021
Hedi Xia, Vai Suliafu, Hangjie Ji, Tan M. Nguyen, Andrea L. Bertozzi, Stanley J. Osher, Bao Wang

Figure 1 for Heavy Ball Neural Ordinary Differential Equations
Figure 2 for Heavy Ball Neural Ordinary Differential Equations
Figure 3 for Heavy Ball Neural Ordinary Differential Equations
Figure 4 for Heavy Ball Neural Ordinary Differential Equations
Viaarxiv icon

FMMformer: Efficient and Flexible Transformer via Decomposed Near-field and Far-field Attention

Aug 05, 2021
Tan M. Nguyen, Vai Suliafu, Stanley J. Osher, Long Chen, Bao Wang

Figure 1 for FMMformer: Efficient and Flexible Transformer via Decomposed Near-field and Far-field Attention
Figure 2 for FMMformer: Efficient and Flexible Transformer via Decomposed Near-field and Far-field Attention
Figure 3 for FMMformer: Efficient and Flexible Transformer via Decomposed Near-field and Far-field Attention
Figure 4 for FMMformer: Efficient and Flexible Transformer via Decomposed Near-field and Far-field Attention
Viaarxiv icon