2025

  • Flow Matching-Based Generative Modeling for Efficient and Scalable Data Assimilation
    Taos Transue*, Bohan Chen*, So Takao, Bao Wang
    arXiv preprint, Aug. 2025
    arXiv
  • Improving Flow Matching by Aligning Flow Divergence
    Yuhao Huang, Taos Transue, Shih-Hsin Wang, William Feldman, Hong Zhang, Bao Wang
    International Conference on Machine Learning (ICML 2025)
    OpenReview
  • A Theoretically-Principled Sparse, Connected, and Rigid Graph Representation of Molecules
    Shih-Hsin Wang*, Yuhao Huang*, Justin Baker, Yuan-En Sun, Qi Tang, Bao Wang
    International Conference on Learning Representations (ICLR 2025, Oral)
    OpenReview
  • Learning Decentralized Swarms Using Rotation Equivariant Graph Neural Networks
    Taos Transue, Bao Wang
    arXiv preprint, Feb. 2025
    arXiv
  • Investigating the Role of Weight Decay in Enhancing Nonconvex SGD
    Tao Sun, Yuhao Huang, Li Shen, Kele Xu, Bao Wang
    Conference on Computer Vision and Pattern Recognition (CVPR 2025)
    OpenReview

2024

  • Towards Practical Overlay Networks for Decentralized Federated Learning
    Yifan Hua, Jinlong Pang, Xiaoxue Zhang, Yi Liu, Xiaofeng Shi, Bao Wang, Yang Liu, Chen Qian
    IEEE 32nd International Conference on Network Protocols (ICNP 2024)
    Conference Proceeding
  • 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