2024
-
An Explicit Frame Construction for Normalizing 3D Point Clouds
Justin Baker*, Shih-Hsin Wang*, Tommaso de Fernex, Bao Wang
International Conference on Machine Learning (ICML 2024)
OpenReview
-
Differentially Private Federated Learning with Laplacian Smoothing
Zhicong Liang, Bao Wang, Quanquan Gu, Stanley Osher, Yuan Yao
Applied and Computational Harmonic Analysis, Vol. 72, 101660, 2024
Journal
-
Rethinking the Benefits of Steerable Features in 3D Equivariant Graph Neural Networks
Shih-Hsin Wang, Yung-Chung Hsu, Justin Baker, Andrea L. Bertozzi, Jack Xin, Bao Wang
International Conference on Learning Representations (ICLR 2024)
OpenReview
-
Efficient Score Matching via Deep Equilibrium Layers
Yuhao Huang, Qingsong Wang, Akwum Onwunta, Bao Wang
International Conference on Learning Representations (ICLR 2024)
OpenReview
-
Monotone Operator Theory-Inspired Message Passing for Learning Long-Range Interaction on Graphs
Justin Baker, Qingsong Wang, Martin Berzins, Thomas Strohmer, Bao Wang
The 27th International Conference on Artificial Intelligence and Statistics (AISTATS 2024)
Conference Proceeding
-
Convergence of Hyperbolic Neural Networks under Riemannian Stochastic Gradient Descent
Wes Whiting, Bao Wang, Jack Xin
Communications on Applied Mathematics and Computation, Volume 6, pages 1175–1188, 2024
Journal
2023
-
Implicit Graph Neural Networks: A Monotone Operator Viewpoint
Justin Baker*, Qingsong Wang*, Cory Hauck, Bao Wang
International Conference on Machine Learning (ICML 2023)
Conference Proceeding
-
Momentum Ensures Convergence of SignSGD under Weaker Assumptions
Tao Sun*, Qingsong Wang*, Dongsheng Li, Bao Wang
International Conference on Machine Learning (ICML 2023)
Conference Proceeding
-
Learning POD of Complex Dynamics Using Heavy-ball Neural ODEs
Justin Baker, Elena Cherkaev, Akil Narayan, Bao Wang
Journal of Scientific Computing, Volume 95, article number 54, 2023
Journal
-
On the Decentralized Stochastic Gradient Descent with Markov Chain Sampling
Tao Sun, Dongsheng Li, Bao Wang
IEEE Transactions on Singal Processing, vol. 71, pp. 2895-2909, 2023
Journal
-
Improving Deep Neural Networks Training for Image Classification with Nonlinear Conjugate Gradient-style Adaptive Momentum
Bao Wang, Qiang Ye
IEEE Transactions on Neural Networks and Learning Systems, doi: 10.1109/TNNLS.2023.3255783, 2023
Journal
-
Accelerated Sparse Recovery via Gradient Descent with Nonlinear Conjugate Gradient Momentum
Mengqi Hu, Yifei Lou, Bao Wang, Ming Yan, Xiu Yang, Qiang Ye
Journal of Scientific Computing, 95:33, 2023.
Journal
-
A Deterministic Approach to Avoid Saddle Points
Lisa Maria Kreusser, Stanley J Osher, Bao Wang
European Journal on Applied Mathematics, Volume 34 Issue 4, Pages 738-757, 2023
Journal
2022
-
Adversarial Attacks on Deep Temporal Point Process
Samira Khorshidi, Bao Wang, George Mohler
In 21st IEEE International Conference on Machine Learning and Applications (ICMLA 2022), Nassau, Dec 12-15, 2022.
-
Finite-Time Analysis of Adaptive Temporal Difference Learning with Deep Neural Networks
Tao Sun, Dongsheng Li, Bao Wang
Advances in Neural Information Processing Systems 35 (NeurIPS 2022)
Conference Proceeding
-
How Does Momentum Benefit Deep Neural Networks Architecture Design? A Few Case Studies
Bao Wang, Hedi Xia, Tan Nguyen, Stanley Osher
Research in Mathematical Sciences,
9 (3) 1-37, 2022
Journal
-
Momentum Transformer: Closing the Performance Gap Between Self-attention and Its Linearization
Tan Nguyen, Richard G. Baraniuk, Robert M. Kirby, Stanley J. Osher, Bao Wang
In Proceeding of Mathematical and Scientific Machine Learning (MSML 2022), Beijing Aug 13-21, 2022.
-
Decentralized Federated Averaging
Tao Sun, Dongsheng Li, Bao Wang
IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE TPAMI) (to appear), 2022
Journal
-
Laplacian Smoothing Gradient Descent
Stanley Osher, Bao Wang, Penghang Yin, Xiyang Luo, Farzin Barekat, Minh Pham, Alex Lin
Research in Mathematical Sciences,
9 (3), 1-26, 2022
Journal
-
Proximal Implicit ODE Solvers for Accelerating Learning Neural ODEs
Justin Baker*, Hedi Xia*, Yiwei Wang, Elena Cherkaev, Akil Narayan, Long Chen, Jack Xin, Andrea L. Bertozzi, Stanley J. Osher, Bao Wang
arXiv preprint, Apr. 2022
arXiv
-
Adaptive and Implicit Regularization for Matrix Completion
Zhemin Li, Tao Sun, Hongxia Wang, Bao Wang
SIAM Journal on Imaging Sciences, Volume 15, Issue 4, Pages 2000-2022, 2022
Journal
-
Efficient and Reliable Overlay Networks for Decentralized Federated Learning
Yifan Hua*, Kevin Miller*, Andrea L Bertozzi, Chen Qian, Bao Wang
SIAM Journal on Applied Mathematics, Vol. 82, Issue 4, pp.1558-1586, 2022
Journal
-
Adaptive Random Walk Gradient Descent for Decentralized Optimization
Tao Sun, Dongsheng Li, Bao Wang
International Conference on Machine Learning (ICML 2022)
Conference Proceeding
-
Glassoformer: a query-sparse transformer for post-fault power grid voltage prediction
Yunling Zheng, Carson Hu, Guang Lin, Meng Yue, Bao Wang, Jack Xin
ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Singapore, 2022
Conference Proceeding
-
GRAND++: Graph Neural Diffusion with A Source Term
Matthew Thorpe*, Hedi Xia*, Tan Nguyen*, Thomas Strohmer, Andrea L. Bertozzi, Stanley J. Osher, Bao Wang
International Conference on Learning Representations (ICLR 2022)
OpenReview
-
Scheduled Restart Momentum for Accelerated Stochastic Gradient Descent
Bao Wang*, Tan Nguyen*, Tan Sun*, Andrea L. Bertozzi, Richard G. Baraniuk, Stanley J. Osher
SIAM Journal on Imaging Sciences, , Vol. 15, Issue 2, pp.738-761, 2022.
Journal| Code
2021
-
Heavy Ball Neural Ordinary Differential Equations
Hedi Xia*, Vai Suliafu*, Hangjie Ji, Tan Nguyen, Andrea L. Bertozzi, Stanley J. Osher, Bao Wang
Advances in Neural Information Processing Systems 34 (NeurIPS 2021)
Conference Proceeding
-
FMMformer: Efficient and Flexible Transformer via Decomposed Near-field and Far-field Attention
Tan Nguyen*, Vai Suliafu*, Stanley J. Osher, Long Chen, Bao Wang
Advances in Neural Information Processing Systems 34 (NeurIPS 2021)
Conference Proceeding
-
Training Deep Neural Networks with Adaptive Momentum Inspired by the Quadratic Optimization
Tao Sun*, Huaming Ling*, Zuoqiang Shi, Dongsheng Li, Bao Wang
arXiv preprint, Oct. 2021
arXiv
-
An Integrated Approach to Produce Robust Models with High Efficiency
Zhijian Li, Bao Wang, Jack Xin
International Conference on Machine Learning, Optimization, and Data Science (LOD 2021). pp.451-465, 2021
Conference Proceeding
Best Paper Award.
-
Deep Interactive Denoiser (DID) for X-Ray Computed Tomography
Ti Bai, Biling Wang, Dan Nguyen, Bao Wang, Bin Dong, Wenxiang Cong, Mannudeep K Kalra, Steve Jiang
IEEE Transactions on Medical Imaging, Vol. 40, Issue 11, pp.2965-2975, 2021
Journal
-
Graph Interpolating Activation Improves Both Natural and Robust Accuracies in Data-Efficient Deep Learning
Bao Wang, Stanley J. Osher
European Journal of Applied Mathematics, Vol. 32, Issue 3, pp.540-569, 2021
Journal| Code
-
Robust Certification for Laplace Learning on Geometric Graphs
Matthew Thorpe, Bao Wang
In Proceeding of Mathematical and Scientific Machine Learning (MSML 2021), Virtual Event Aug 16-19th, 2021.
Conference Page
-
Stability and Generalization of the Decentralized Stochastic Gradient Descent
Tao Sun, Dongsheng Li, Bao Wang
Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI-21).
Conference Proceeding
-
Convergence of the Weighted Nonlocal Laplacian on Random Point Cloud
Zuoqiang Shi, Bao Wang
Journal of Computational Mathematics, Vol. 39, Issue 6, pp.865, 2021
Journal
-
Laplacian Smoothing Stochastic Gradient Markov Chain Monte Carlo
Bao Wang*, Difan Zou*, Quanquan Gu, Stanley Osher
SIAM Journal on Scientific Computing, Vol. 43, Issue 1, pp.A26-A53, 2021
Journal
2020
-
MomentumRNN: Integrating Momentum into Recurrent Neural Networks
Tan M. Nguyen, Richard G. Baraniuk, Andrea L. Bertozzi, Stanley J. Osher, Bao Wang
Advances in Neural Information Processing Systems 33 (NeurIPS 2020)
Conference Proceeding| Code
-
Monodisperse drops templated by 3D-structured microparticles
Chueh-Yu Wu, Mengxi Ouyang, Bao Wang, Joseph de Rutte, Mengxing Ouyang, Alexis Joo, Matthew Jacobs, Kyung Ha, Andrea Bertozzi, Dino Di Carlo
Science Advances, Vol. 6, Issue 45, pages eabb9023, 2020
Journal
-
DP-LSSGD: A Stochastic Optimization Method to Lift the Utility in Privacy-Preserving ERM
Bao Wang, Quanquan Gu, March Boedihardjo, Lingxiao Wang, Farzin Barekat, Stanley J Osher
In Proceeding of Mathematical and Scientific Machine Learning (MSML 2020), Princeton, NJ, Jul. 2020
PDF
-
Sparsity Meets Robustness: Channel Pruning for the Feynman-Kac Formalism Principled Robust Deep Neural Nets
Thu Dinh*, Bao Wang*, Andrea L. Bertozzi, Stanley J. Osher, Jack Xin
International Conference on Machine Learning, Optimization, and Data Science (LOD 2020). pp.362-381, 2020
Conference Proceeding
-
EnResNet: ResNets Ensemble via the Feynman--Kac Formalism for Adversarial Defense and Beyond
Bao Wang, Binjie Yuan, Zuoqiang Shi, Stanley J Osher
SIAM Journal on Mathematics of Data Science, Vol. 2, No. 3, pp.559-2582, 2020
Journal
-
Adversarial Defense via Data-dependent Activation Function and Total Variation Minimization
Bao Wang, Alex T Lin, Zuoqiang Shi, Wei Zhu, Penghang Yin, Andrea L Bertozzi, Stanley J Osher
Inverse Problems and Imaging, Vol. 15, No. 1, pp.129-145, 2020
Journal
2019
-
ResNets Ensemble via the Feynman-KAC Formalism to Improve Natural and Robust Accuracies
Bao Wang, Binjie Yuan, Zuoqiang Shi, Stanley Osher
Advances in Neural Information Processing Systems 32 (NeurIPS 2019), Vancouver, Dec. 2019
Conference Proceeding
-
Deep Learning for Real-time Crime Forecasting and its Ternarization
Bao Wang, Penghang Yin, Andrea Louise Bertozzi, P Jeffrey Brantingham, Stanley Joel Osher, Jack Xin
Chinese Annals of Mathematics, Series B, Vol. 40, No. 6, pp.949-966, 2019
Journal
-
SOS-EW: System for Overdose Spike Early Warning Using Drug Mover’s Distance-based Hawkes Processes
Wen-Hao Chiang, Baichuan Yuan, Hao Li, Bao Wang, Andrea Bertozzi, Jeremy Carter, Brad Ray, George Mohler
Joint European Conference on Machine Learning and Knowledge Discovery in Databases, Sep. 2019
Conference Proceeding
-
Stop Memorizing: A Data-dependent Regularization Framework for Intrinsic Pattern Learning
Wei Zhu, Qiang Qiu, Bao Wang, Jianfeng Lu, Guillermo Sapiro, Ingrid Daubechies
SIAM Journal on Mathematics of Data Science, Vol. 1, No. 3, pp.476-496, 2019
Journal
-
A Study on Graph-Structured Recurrent Neural Networks and Sparsification with Application to Epidemic Forecasting
Zhijian Li, Xiyang Luo, Bao Wang, Andrea L. Bertozzi, Jack Xin
Proc. World Congress Global Optimization, Metz, France, July 2019
Conference Proceeding
2018
-
Deep Neural Nets with Interpolating Function as Output Activation
Bao Wang, Xiyang Luo, Zhen Li, Wei Zhu, Zuoqiang Shi, Stanley J. Osher
Advances in Neural Information Processing Systems 31 (NeurIPS 2018), Vancouver, Dec. 2018
Conference Proceeding
-
Mathematical Analysis of Adversarial Attacks
Zehao Dou, Stanley J Osher, Bao Wang
arXiv preprint, Nov. 2018
arXiv
-
Graph-based Deep Modeling and Real-time Forecasting of Sparse Spatio-temporal Data
Bao Wang, Xiyang Luo, Fangbo Zhang, Baichuan Yuan, Andrea L Bertozzi, P Jeffrey Brantingham
4th Workshop on Mining and Learning from Time Series (MileTS), KDD, London, Aug. 2018.
Paper|arXiv
-
Scientific Data Interpolation with Low Dimensional Manifold Model
Wei Zhu, Bao Wang, Richard Barnard, Cory D. Hauck, Frank Jenko, Stanley J. Osher
Journal of Computational Physics, Vol. 352, pp.213-245, 2018
Journal
2017
-
Deep Learning for Real-time Crime Forecasting
Bao Wang, Duo Zhang, Duanhao Zhang, P. Jeffery Brantingham, Andrea L. Bertozzi
2017 International Symposium on Nonlinear Theory and Its Applications (NOLTA), Cancun, Mexico, Dec. 2017
Conference Proceeding|arXiv
-
Finite Volume Formulation of the MIB Method for Elliptic Interface Problems
Yin Cao, Bao Wang, K Xia, G Wei
Journal of Computational and Applied Mathematics, Vol. 321, pp.60-77, 2017
Journal
-
Accurate, Robust, and Reliable Calculations of Poisson–Boltzmann Binding Energies
DD Nguyen, Bao Wang, GW Wei
Journal of computational chemistry, Vol. 38, No. 13, pp.941-948, 2017
Journal
-
Feature Functional Theory–Binding Predictor (FFT–BP) for the Blind Prediction of Binding Free Energies
Bao Wang, Zhixiong Zhao, DD Nguyen, GW Wei
Theoretical Chemistry Accounts, Vol. 136, No. 4, 2017
Journal
-
ESES: Software for Eulerian Solvent Excluded Surface
B Liu, B Wang, R Zhao, Y Tong, GW Wei
Journal of Computational Chemistry, Vol. 38, No. 7, pp.446-466, 2017
Journal
2016
-
Automatic Parametrization of Non-polar Implicit Solvent Models for the Blind Prediction of Solvation Free Energies
B Wang, Z Zhao, GW Wei
The Journal of chemical physics, Vol. 145, No. 12, 124110, 2016
Journal
-
Object-oriented Persistent Homology
B Wang, GW Wei
Journal of computational physics, Vol. 305, pp.276-299, 2016
Journal
2015
-
Parameter Optimization in Differential Geometry-based Solvation Models
B Wang, GW Wei
The Journal of chemical physics, Vol. 143, No. 13, 10B608, 2015
Journal
-
Second-order Method for Solving 3D Elasticity Equations with Complex Interfaces
B Wang, K Xia, G Wei
Journal of computational physics, Vol. 294, pp.405-438, 2015
Journal
-
Matched Interface and Boundary Method for Elasticity Interface Problems
B Wang, K Xia, GW Wei
Journal of computational and applied mathematics, Vol. 205, No. 10, pp.203-225, 2015
Journal