Bao Wang
Assistant Adjunct Professor
I am a postdoc at Department of Mathematics of UCLA,
under the mentorship of Professors Andrea L.
Bertozzi and Stanley J. Osher.
My research interest lies in an synergistic integration of machine learning with first principlebased approaches.
I work on developing firstprinciple inspired conceptually simple, computationally efficient and theoretically principled
optimization and sampling algorithms and novel architectures to pursue robust, accurate, private, and dataefficient deep learning.
Also, I integrate advanced deep learning algorithms into the classical first principlebased models to advance molecularscale modeling and
computation of the biological systems.
I received my Ph.D. degree in Applied Mathematics from the Michigan State University (20122016). Here is my latest CV.
Recent Activities (Since 2018)
Recent Research Highlight

DPLSSGD: A Stochastic Optimization Method to Lift the Utility in PrivacyPreserving ERM
Bao Wang, Quanquan Gu, March Boedihardjo, Farzin Barekat, and Stanley J. Osher, arXiv:1906.12056, 2019.

ResNet Ensemble via the FeynmanKac Formalism to Improve Robust and Natural Accuracies
Bao Wang, Binjie Yuan, Zuoqiang Shi and Stanley J. Osher, In Proc. of Advances in Neural Information Processing Systems (NeurIPS) 32, Vancouver, Canada, 2019.

Laplacian Smoothing Gradient Descent
Stanley Osher, Bao Wang, Penghang Yin, Xiyang Luo, Minh Pham and Alex Lin, arXiv:1806.06317, 2018.

GraphBased Deep Modeling and Real Time Forecasting of Sparse SpatioTemporal Data
Bao Wang*, Xiyang Luo*, Fangbo Zhang*, Baichuan Yuan, Andrea L. Bertozzi and P. Jeffrey Brantingham, Mining and Learning from Time Series (MileTS), KDD, 2018.

Deep Neural Nets with Interpolating Function as Output Activation
Bao Wang, Xiyang Luo, Zhen Li, Wei Zhu, Zuoqiang Shi and Stanley Osher, In Proc. of Advances in Neural Information Processing Systems (NeurIPS) 31, MontrĂ©al, Canada, 2018.
Contact
Address: 7310 Math Science Building, Los Angeles, CA 90095
Email: wangbao@math.ucla.edu, wangbaonj@gmail.com
Phone: 5178996124
