Education

Ph.D. in Mathematics, National University of Singapore, 2014

Supervisors: Prof. Hui Ji and Prof. Defeng Sun

B.Sc. in Mathematics, Sun Yat-Sen University, 2009

Work Experience

Research fellow, Deparment of mathematics, National University of Singapore, 2015-2017 Supervisor: Prof. Zuowei Shen

Assistant Professor, Yau Mathematical Sciences Center, 2018.04-present

Publications

Preprints

·Semi-Supervised Clustering via Dynamic Graph Structure Learning

Huaming Ling, Chenglong Bao, Xin Liang, Zuoqiang Shi. ArXiv:2209.02513. [pdf]

·Convergence Rates of Training Deep Neural Networks via Alternating Minimization Methods

Jintao Xu, Chenglong Bao, Wenxun Xing. ArXiv:2208.14318. [pdf]

On the robust isolated calmness of a class of nonsmooth optimizations on Riemannian manifolds and its applications

Yuexin Zhou, Chenglong Bao, Chao Ding. ArXiv:2208.07518. [pdf]

·A Scalable Deep Learning Approach for Solving High-dimensional Dynamic Optimal Transport

Wei Wan, Yuejin Zhang, Chenglong Bao, Bin Dong, Zuoqiang Shi. ArXiv:2205.07521. [pdf]

·Diffusion Mechanism in Neural Network: Theory and Applications

Tangjun Wang, Zehao Dou, Chenglong Bao, Zuoqiang Shi. Arxiv:2105.03155. [pdf]

·Tightness and Equivalence of Semidefinite Relaxations for MIMO Detection

Ruichen Jiang, Ya-Feng Liu, Chenglong Bao, Bo Jiang. Arxiv:2102.04586. [pdf]

·Approximation Analysis of Convolutional Neural Networks

Chenglong Bao, Qianxiao Li, Zuowei Shen, Cheng Tai, Lei Wu, Xueshuang Xiang. submitted. [pdf]

Journal papers

·Learn from Unpaired Data for Image Restoration: A Variational Bayes Approach

Dihan Zheng, Xiaowen Zhang, Kaisheng Ma, Chenglong Bao. IEEE Transactions on Pattern Analysis and Machine Intelligence, accepted, 2022 [pdf]

·A Semismooth Newton based Augmented Lagrangian Method for Nonsmooth Optimization on Matrix Manifolds

Yuhao Zhou, Chenglong Bao, Chao Ding, Jun Zhu, Mathematical Programming, 2022. [pdf][Code]

·Unsupervised Deep Learning Meets Chan-Vese Model

Dihan Zheng, Chenglong Bao, Zuoqiang Shi, Haibin Ling, Kaisheng Ma. CSIAM Transactions on Applied Mathematics, accepted, 2022. [pdf][Code]

·Self-Distillation: Towards Efficient and Compact Neural Networks

Linfeng Zhang, Chenglong Bao, Kaisheng Ma. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(8), 4388-4403 2022. [pdf]

·Adapting the Residual Dense Network for Seismic Data Denoising and Upscaling

Rongqian Wang, Ruixuan Zhang, Chenglong Bao, Lingyun Qiu, Dinghui Yang. Geophysics, 87(4), V321-V340, 2022. [pdf]

·Improved Harmonic Incompatibility Removal for Susceptibility Mapping via Reduction of Basis Mismatch

Chenglong Bao, Jian-Feng Cai, Jae Kyu Choi, Bin Dong, Ke Wei. Journal of Computational Mathematics, 40(6), 914–937, 2022.

·An adaptive block Bregman proximal gradient method for computing stationary states of multicomponent phase-field crystal model

Chenglong Bao, Chang Chen, Kai Jiang. CSIAM Transactions on Applied Mathematics, 3(1), 133-171, 2022. [pdf]

·Zero Norm based Analysis Model for Image Smoothing and Reconstruction

Jiebo Song, Jia Li, Zhengan Yao, Kaisheng Ma, Chenglong Bao. Inverse Problems, 36(11), 2020. [pdf]

·Efficient Numerical Methods for Computing the Stationary States of Phase Field Crystal Models

Kai Jiang, Wei Si, Chang Chen, Chenglong Bao. SIAM Journal on Scientific Computing, 42(6), B1350–B1377, 2020. [pdf]

·Barzilai-Borwein-based adaptive learning rate for deep learning

Jinxiu Liang, Yong Xu, Chenglong Bao, Yuhui Quan, Hui Ji. Pattern Recognition Letters , 128(1), 197-203, 2019. [pdf]

·Whole brain susceptibility mapping using harmonic incompatibility removal

Chenglong Bao, Jae Kyu Choi, and Bin Dong. SIAM Journal on Imaging Science,12(1), 492-520,2019. [pdf]

·Investigating energy-based pool structure selection in the structure ensemble modeling with experimental distance constraints: the example from a molti-domain protein Pub 1

Guanhua Zhu, Wei Liu, Chenglong Bao, Dudu Tong, Hui Ji, Zuowei Shen, Daiwei Yang, and Lanyuan Lu. Proteins: Structure, Function, and Bioinformatics, 86 (5), 501–514, 2018.[pdf]

·PET-MRI joint reconstruction by joint sparsity based tight frame regolarization

Jae Kyu Choi, Chenglong Bao, and Xiaoqun Zhang. SIAM Journal on Imaging Sciences, 11 (2), 1179–1204, 2018. [pdf]

·Coherence retrieval using trace regolarization

Chenglong Bao, George Barbastathis, Hui Ji, Zuowei Shen, and Zhengyun Zhang. SIAM Journal on Imaging Sciences, 11 (1), 679–706, 2018. [pdf]

·Apparent coherence loss in phase space tomography

Zhengyun Zhang, Chenglong Bao, Hui Ji, Zuowei Shen, and George Barbastathis. Journal of the Optical Society of America A, 34 (11), 2025–2033, 2017.[pdf]

·Image restoration by minimizing zero norm of wavelet frame coefficients

Chenglong Bao, Bin Dong, Likun Hou, Zuowei Shen, Xiaoqun Zhang, and Xue Zhang. Inverse Problems, 32 (1), 2016. [pdf]

·Cerebellar functional parcellation using sparse dictionary learning clustering

Changqing Wang, Judy Kipping, Chenglong Bao, Hui Ji, and Anqi Qiu. Frontiers in Neuroscience, 10 (188), 2016 [pdf]

·Dictionary learning for sparse coding: algorithms and convergence analysis

Chenglong Bao, Hui Ji, Yuhui Quan, and Zuowei Shen. IEEE Transactions on Pattern Analysis and Machine Intelligence, 38 (7), 1356–1369, 2016. [pdf][Code]

·Convergence analysis for iterative data-driven tight frame construction scheme

Chenglong Bao, Hui Ji, and Zuowei Shen. Applied and Computational Harmonic Analysis, 38 (3), 510–523, 2015. [pdf]

Conference papers

·A Variant of Anderson Mixing with Minimal Memory Size

Fuchao Wei, Chenglong Bao, Yang Liu, Guangwen Yang. NeurIPS, 2022.

·A Class of Short-term Recurrence Anderson Mixing Methods and Their Applications

Fuchao Wei, Chenglong Bao, Yang Liu. ICLR, 2022. [pdf]

·Stochastic Anderson Mixing for Nonconvex Stochastic Optimization

Fuchao Wei, Chenglong Bao, Yang Liu. NeurIPS, 2021. [pdf][Code]

·AFEC: Active Forgetting of Negative Transfer in Continual Learning

Liyuan Wang, Mingtian Zhang, Zhongfan Jia, Qian Li, Chenglong Bao, Kaisheng Ma, Jun Zhu, Yi Zhong. NeurIPS, 2021. [pdf]

·Seismic Data Denoising and Interpolation Using Deep Learning

Rongqian Wang, Ruixuan Zhang, Chenglong Bao, Lingyun Qiu, Dinghui Yang. EAGE Annual Conference and Exhibition, 2021. [pdf]

·Seismic Waveform Inversion with Source Manipulation

Rongqian Wang, Chenglong Bao, Lingyun Qiu. EAGE Annual Conference and Exhibition, 2021. [pdf]

·Wavelet J-Net: A Frequency Perspective on Convolutional Neural Networks

Linfeng Zhang, Xiaoman Zhang, Chenglong Bao, Kaisheng Ma. IJCNN, 2021. [pdf]

·An Unsupervised Deep Learning Approach for Real-World Image Denoising

Dihan Zheng, Sia Huat Tan, Xiaowen Zhang, Zuoqiang Shi, Kaisheng Ma, Chenglong Bao. ICLR, 2021. [pdf] [Code]

·Task-Orientated Feature Distillation

Linfeng Zhang, Yukang Shi, Zuoqiang Shi, Kaisheng Ma, Chenglong Bao. NeurIPS 2020. [pdf][Code]

·Interpolation between Residual and Non-Residual Networks

Zonghan Yang, Yang Liu, Chenglong Bao, Zuoqiang Shi. ICML 2020. [pdf][Code]

·Auxiliary Training: Towards Accurate and Robust Models

Linfeng Zhang, Muzhou Yu, Tong Chen, Zuoqiang Shi, Chenglong Bao, Kaisheng Ma. CVPR 2020. [pdf][Code]

·Light-weight Calibrator: a Separable Component for Unsupervised Domain Adaptation

Shaokai Ye, Kailu Wu, Mu Zhou, Yunfei Yang, Sia huat Tan, Kaidi Xu, Jiebo Song, Chenglong Bao, Kaisheng Ma. CVPR 2020. [pdf]

·Robust Document Distance with Wasserstein-Fisher-Rao Metric

Zihao Wang, Datong Zhou, Yong Zhang, Chenglong Bao, Hao Wu. ACML 2020. [pdf]

·SCAN: A Scalable Neural Networks Framework Towards Compact and Efficient Models

Linfeng Zhang, Zhanhong Tan, Jiebo Song, Jingwei Chen, Chenglong Bao, and Kaisheng Ma. NeurIPS. Vancouver, 2019. [pdf][Code]

·Be your own teacher: improve the performance of convolutional neural networks via self distillation

Linfeng Zhang, Jiebo Song, Anni Gao, Jingwei Chen, Chenglong Bao, and Kaisheng Ma. ICCV, Seoul, 2019. [pdf][Code]

·Equiangular kernel dictionary learning with applications to dynamic texture analysis

Yuhui Quan, Chenglong Bao, and Hui Ji. CVPR, Las Vegas, 2016 [pdf]

·A convergent incoherent dictionary learning algorithm for sparse coding

Chenglong Bao, Yuhui Quan, and Hui Ji. ECCV, Zurich, 2014. [pdf]

·L0 norm based dictionary learning by proximal methods with global convergence

Chenglong Bao, Hui Ji, Yuhui Quan, and Zuowei Shen. CVPR, Columbus, 2014. [pdf]

·Fast sparsity based orthogonal dictionary learning for image restoration

Chenglong Bao, Jian-feng Cai, and Hui Ji. ICCV, Sydney,2013. [pdf]

·Real time robust L1 tracker using accelerated proximal gradient method

Chenglong Bao, Yi Wu, Haibin Ling, and Hui Ji. CVPR, Rhole Island, 2012. [pdf]