Dr. Zhanxing Zhu (朱占星)
@ Peking University (北京大学)
Welcome to my homepage!
I am now Assistant Professor at School of Mathematical Sciences, and Center for Data Science (大数据科学研究中心), Peking University (北京大学). I am closely affiliated with Deep Learning Lab of Peking University (北京大学深度学习实验室). Previously, I obtained my PhD in machine learning from School of Informatics of University of Edinburgh, UK.
My research interests cover methodology/theory of machine learning and artificial intelligence and their applications in various areas.
Methodology/theory: deep learning, reinforcement learning, scalable optimization and Bayesian inference methods
Applications: prediction problems in traffic, data-driven medical imaging, generative models and reinforcement learning for computer graphics and network security
Contact: Room 219, Jingyuan 6th Courtyard, Peking University, Beijing, 100871, China (北京大学静园6号院219)
Ph.D students: Bing Yu ( co-supervised with Prof. Weinan E), Yizheng Hu
MPhil students: Junzhao Zhang, Jin Ma.
Undergraduate: Pu Yang, Zehao Wang.
Publications/Preprints [Sorted by Research Topics]
* indicates equal contribution. (Check our Github page for reproducibility.)
Wan, Ruosi*, Zhanxing Zhu*, Xiangyu Zhang, and Jian Sun. Spherical Motion Dynamics of Deep Neural Networks with Batch Normalization and Weight Decay. arXiv preprint.
Bing Yu*, Junzhao Zhang* and Zhanxing Zhu. "On the Learning Dynamics of Two-layer Nonlinear Convolutional Neural Networks". arXiv pre-print.
Guangda Ji and Zhanxing Zhu. Knowledge Distillation in Wide Neural Networks: Risk Bound, Data Efficiency and Imperfect Teacher. 34th Annual Conference on Neural Information Processing Systems (NeurIPS 2020).
Dinghuai Zhang*, Mao Ye*, Chengyue Gong*, Zhanxing Zhu and Qiang Liu. Black-Box Certification with Randomized Smoothing: A Functional Optimization Based Framework. 34th Annual Conference on Neural Information Processing Systems (NeurIPS 2020).
Jingfeng Wu, Wenqing Hu, Haoyi Xiong, Jun Huan, Vladimir Braverman and Zhanxing Zhu. On the Noisy Gradient Descent that Generalizes as SGD. 37th International Conference on Machine Learning (ICML 2020).
Yanzhi Chen, Renjie Xie and Zhanxing Zhu. On Breaking Deep Generative Model-based Defenses and Beyond. 37th International Conference on Machine Learning (ICML 2020).
Baifeng Shi, Dinghuai Zhang, Qi Dai, Jingdong Wang, Zhanxing Zhu and Yadong Mu. Informative Dropout for Robust Representation Learning: A Shape-bias Perspective. 37th International Conference on Machine Learning (ICML 2020) [Code].
Guixin Ye, Zhanyong Tang, Dingyi Fang, Zhanxing Zhu, Yansong Feng, Pengfei Xu, Xiaojiang Chen, Jungong Han and. Zheng Wang. Using Generative Adversarial Networks to Break and Protect Text Captchas. ACM Transactions on Privacy and Security, 2019. (TOPS).
Ke Sun, Zhouchen Lin and Zhanxing Zhu. Multi-Stage Self-Supervised Learning for Graph Convolutional Networks on Graphs with Few Labeled Nodes. The 34th AAAI Conference on Artificial Intelligence. (AAAI 2020)
Quanming Yao*, Ju Xu*, Wei-wei Tu and Zhanxing Zhu. Efficient Neural Architecture Search via Proximal Iterations. The 34th AAAI Conference on Artificial Intelligence. (AAAI 2020)
Ju Xu*, Mengzhang Li* and Zhanxing Zhu. Automatic Data Augmentation for 3D Medical Image Segmentation. 23rd International Conference on Medical Image Computing and Computer Assisted Interventions (MICCAI 2020)
Hantao Guo, Rui Yan, Yansong Feng, Xuesong Gao and Zhanxing Zhu. Simplifying Graph Attention Networks with Source-Target Separation. The 24th European Conference on Artificial Intelligence (ECAI 2020)
Lei Wu, Zhanxing Zhu. Towards Understanding and Improving the Transferability of Adversarial Examples in Deep Neural Networks. The 12th Asian Conference on Machine Learning. (ACML 2020)
Dinghuai Zhang*, Tianyuan Zhang*, Yiping Lu*, Zhanxing Zhu and Bin Dong. You Only Propagate Once: Accelerating Adversarial Training Using Maximal Principle. 33rd Annual Conference on Neural Information Processing Systems (NeurIPS 2019). [Code]
Zhanxing Zhu*, Jingfeng Wu*, Bing Yu, Lei Wu and Jinwen Ma. The Anisotropic Noise in Stochastic Gradient Descent: Its Behavior of Escaping from Minima and Regularization Effects. 36th International Conference on Machine Learning (ICML 2019) [Code]
Tianyuan Zhang, Zhanxing Zhu. Interpreting Adversarial Trained Convolutional Neural Networks. 36th International Conference on Machine Learning. (ICML 2019) [Code]
Bing Yu*, Jingfeng Wu*, Jinwen Ma and Zhanxing Zhu. Tangent-Normal Adversarial Regularization for Semi-supervised Learning. The 30th IEEE Conference on Computer Vision and Pattern Recognition. (CVPR 2019 Oral ) [Code]
He Wang , Edmond S. L. Ho , Hubert P. H. Shum , and Zhanxing Zhu. Spatio-temporal Manifold Learning for Human Motions via Long-horizon Modeling. IEEE Transactions on Visualization and Computer Graphics, 2019 (TVCG)
Ruosi Wan, Mingjun Zhong, Haoyi Xiong and Zhanxing Zhu. Neural Control Variates for Monte Carlo Variance Reduction. The European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases. (ECML/PKDD 2019) [Code]
Kafeng Wang, Haoyi Xiong, Jiang Bian, Zhanxing Zhu, Chengzhong Xu, Zhishan Guo, Jun Huan. SpHMC: Spectral Hamiltonian Monte Carlo. 33rd AAAI Conference on Artificial Intelligence. (AAAI 2019)
Ruosi Wan, Haoyi Xiong, Xingjian Li, Zhanxing Zhu, and Jun Huan. Towards Making Deep Transfer Learning Never Hurt. The International Conference on Data Mining. (ICDM 2019) (Regular paper)
Xiantong Zou, Xianghai Zhou, Zhanxing Zhu and Linong Ji. Novel subgroups of patients with adult-onset diabetes in Chinese and US populations. Lancet (Diabetes and Endocrinology) 2019.
Ke Sun, Hangao Guo, Zhouchen Lin, and Zhanxing Zhu. Virtual Adversarial Training on Graph Convolutional Networks in Node Classification. Chinese Conference on Pattern Recognition and Computer Vision (PRCV 2019 Oral)
Sen Hu, Lei Zou and Zhanxing Zhu. How Question Generation Can Help Question Answering over Knowledge Base? International Conference on Natural Language Processing and Chinese Computing (NLPCC 2019)
Rui Luo, Yaodong Yang, Jianhong Wang, Zhanxing Zhu, Jun Wang. Thermostat-assisted continuously-tempered Hamiltonian Monte Carlo for Bayesian learning. 32nd Annual Conference on Neural Information Processing Systems (NeurIPS 2018) [Code].
Guixin Ye, Zhanyong Tang, Dingyi Fang, Zhanxing Zhu, Yansong Feng, Pengfei Xu, Xiaojiang Chen, Zheng Wang. Yet Another Text Captcha Solver: A Generative Adversarial Network Based Approach. 25th ACM Conference on Computer and Communications Security . (CCS 2018) (Best Paper Award Finalists) [Code]
Bing Yu*, Haoteng Yin*, Zhanxing Zhu. Spatio-temporal Graph Convolutional Neural Network: A Deep Learning Framework for Traffic Forecasting. 27th International Joint Conference on Artificial Intelligence . (IJCAI 2018) [Code]
Nanyang Ye, Zhanxing Zhu. Stochastic Fractional Hamiltonian Monte Carlo. 27th International Joint Conference on Artificial Intelligence. (IJCAI 2018)
Huizhuo Yuan, Jinzhu Jia and Zhanxing Zhu. SIPID: A Deep Learning Framework for Sinogram Interpolation and Image Denoising in Low-Dose CT Reconstruction. In 2018 IEEE International Symposium on Biomedical Imaging (ISBI 2018 Oral )[Code]
Nanyang Ye, Zhanxing Zhu, Rafal K. Mantiuk. Langevin Dynamics with Continuous Tempering for Training Deep Neural Networks. 31st Annual Conference on Neural Information Processing Systems. (NIPS 2017)
Lei Wu, Zhanxing Zhu and Weinan E. Towards Understanding Generalization of Deep Learning: Perspective of Loss Landscapes. 34th International Conference on Machine Learning. (ICML 2017 W.)
Bingfeng Luo, Yansong Feng, Zheng Wang, Zhanxing Zhu, Songfang Huang, Rui Yan and Dongyan Zhao. Learning with Noise: Enhance Distantly Supervised Relation Extraction with Dynamic Transition Matrix. 55th Annual Meeting of the Association for Computational Linguistics. (ACL 2017)
Zhanxing Zhu and Amos Storkey. Stochastic Parallel Block Coordinate Descent for Large-scale Saddle Point Problems. Thirtieth AAAI Conference on Artificial Intelligence (AAAI 2016)
Zhanxing Zhu*, Xiaocheng Shang*, Benedict Leimkuhler and Amos Storkey. Covariance-Controlled Adaptive Langevin Thermostat for Large-Scale Bayesian Sampling. 29th Annual Conference on Neural Information Processing Systems (NIPS 2015)
Zhanxing Zhu and Amos Storkey. Adaptive Stochastic Primal-Dual Coordinate Descent for Separable Saddle Point Problems. European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML/PKDD 2015)
Amos Storkey, Zhanxing Zhu and Jinli Hu. Aggregation Under Bias: Renyi Divergence Aggregation and its Implementation via Machine Learning Markets. European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases. (ECML/PKDD 2015)
Amos Storkey, Zhanxing Zhu, Jinli Hu. A Continuum from Mixtures to Products: Aggregation under Bias. 31st International Conference on Machine Learning (ICML 2014 Workshop on Divergence Methods for Probabilistic Inference).
Francesco Corona, Zhanxing Zhu, Amauri Holanda de Souza Júnior, Michela Mulas, Emanuela Muru, Lorenzo Sassu, Guilherme Barreto, and Roberto Baratti. Supervised Distance Preserving Projections: Applications in the quantitative analysis of diesel fuels and light cycle oils from NIR spectra. Journal of Process Control (2014)
Zhanxing Zhu, Zhirong Yang and Erkki Oja. Multiplicative Updates for Learning with Stochastic Matrices. In the 18th Conference Scandinavian Conferences on Image Analysis (SCIA 2013) (Oral presentation).
Zhanxing Zhu, Timo Simila and Francesco Corona. Supervised Distance Preserving Projection. Neural Processing Letters 38(3): 445-463 (2013)
Zhanxing Zhu, Francesco Corona, Amaury Lendasse, Roberto Baratti and Jose A. Romagnoli. Local linear models for soft-sensor design with application to an industrial deethanizer. 18th World Congress of the International Federation of Automatic Control (IFAC) , Milan, Italy, 2011.
Zhirong Yang, Zhanxing Zhu and Erkki Oja. Automatic Rank Determination in Projective Nonnegative Matrix Factorization. 9th International Conference on Latent Variable Analysis and Signal Separation (LVA/ICA 2010).
" Only in silence the word, only in dark the light, only in dying life: bright the hawk's flight on the empty sky. "
— Ursula K. Le Guin (A Wizard of Earthsea)
Recently, I wrote a book in Chinese with several colleagues on the introduction to data science "数据科学导引". Welcome for all kinds of feedback!
Ju Xu (Master, 2020. now soft engineer @Alibaba)
Yuanjin Zhu (Master, 2020. now soft engineer @Alibaba)
Hantao Guo (Master, 2020. now soft engineer @Yuanfudao)
Ke Sun (Master, 2020. now Ph.D student @ U of Alberta)
Ruosi Wan (Master, 2019. now research scientist @ MEGVII)
Haoteng Yin (Master, 2019. now Ph.D student @ Purdue University)
Jingfeng Wu (Master, 2019. now Ph.D student @ John Hopkins University)
Zizhuo Zhang (Master, 2019)
Mengzhang Li (Master, 2019. Software Engineer@Canon Medical Systems (China))
Dinghuai Zhang (Bachelor, 2020. now Ph.D student @ Mila)
Tianyuan Zhang (Bachelor, 2020. now soft engineer @ByteDance)
Qianli Shen (Bachelor, 2020. now intern @Huawei)
Yunsong Lan (Bachelor, 2020. now teacher@Xueersi)