MATHEMATICS OF GEOMETRIC
DEEP LEARNING

Teresa is a PhD candidate in the Department of Applied Mathematics & Statistics at Johns Hopkins University. She is co-advised by Professor Soledad Villar and Professor Carey Priebe. She is passionate about understanding learning — including machine learning and natural learning — from mathematical and statistical principles. Her research interests are in the areas of representation learning and deep learning. Her current work focuses on spectral-inspired graph neural networks, and generalization and robustness in deep learning.

Prof Lin Liu is an Assistant Professor at the Institute of Natural Sciences (INS) at Shanghai Jiao Tong University (SJTU). I am also affiliated with the School of Mathematical Sciences and the SJTU-YALE Joint Center for Biostatistics and Data Science. He graduated from the Department of Biostatistics at Harvard University in 2018. His advisors are Professor Franziska Michor and Professor James M. Robins. His current research lies in nonparametric, semiparametric and high-dimensional statistics, robust statistical methods, causal inference, computational and mathematical biology. He is also interested in the theory of deep learning, estimation and inference in inverse problems and applying causal inference tools in biomedical research.

Qi Ye received the Ph.D. degree in applied mathematics from Illinois Institute of Technology in 2012. Now he is a professor of School of Mathematical Sciences and the director of Laboratory for Machine Learning and Computational Optimization at South China Normal University. He received the Sigma Xi Award at Chicago in 2012. His researches focus on the approximation theory to machine learning and data analysis such as kernel-based approximation methods. His original research of sparse machine learning is published in Memoirs of the American Mathematical Society. The sparse learning algorithms are already applied to the big data analysis of education and medicine to develop the educational and medical softwares. Now he will combine the model‑driven and data‑driven methods to construct the composite algorithms to develop the new learning methods.

Yiqing is a CS Ph.D. Student of Johns Hopkins University. He obtained his bachelor degree from Shanghai Jiao Tong University. His research interests span the fields of medical image analysis, computer vision, and particularly, their interdisciplinary direction.

...

Dr Huan Xiong is currently a Full Professor and Department Vice Director at the Harbin Institute of Technology, and an Adjunct Assistant Professor at the Mohamed bin Zayed University of Artificial Intelligence. Previously, he was a postdoctoral researcher at the University of Strasbourg, France. He received the B.S. and M.S. degrees from the School of Mathematical Sciences, Peking University, China, in 2010 and 2013, respectively, and the Ph.D. degree from the University of Zurich, Switzerland, in 2016. His research interests include Machine Learning and Discrete Mathematics. He has published over 30 papers in top journals/conferences such as TPAMI, ICML, NeurIPS, AAAI, CVPR, ICCV and ECCV. He has organized the conferences “Combinatorics and its Applications” at the Harbin Institute of Technology in 2018, and “Workshop on Combinatorics and Graph Theory” at the Harbin Institute of Technology in 2021.

Dr Junyu Xuan is an ARC Discovery Early Career Researcher Award (DECRA) Fellow and Senior Lecturer of Australia Artificial Intelligence Institute in Faculty of Engineering and IT at the University of Technology Sydney (UTS). He received a dual-doctoral degree from the University of Technology Sydney and Shanghai University in 2016. After his Ph.D., he worked as a Postdoctoral Research Fellow in the Faculty of Engineering and IT of the University of Technology Sydney in Australia for three years. In 2020, he secured an ARC Discovery Early Career Researcher Award and became a Lecturer at UTS.

Dr Xuan’s research interests include Machine Learning, Bayesian Nonparametric Learning, Text Mining, Web Mining, etc. He has published over 40 papers in high-quality journals and conferences, including Artificial Intelligence Journal, Machine Learning Journal, IEEE TNNLS, IEEE TFS, IEEE TKDE, IEEE TCYB, ACM TOIS, ACM TIST, ACM Computing Surveys, ICDM, NeurIPS, AAAI, IJCNN, etc. He severed as PC or Senior PC member for conferences, e.g. NIPS, ICML, ICLR, ACML, IJCAI, AAAI, IJCNN, ICONIP, etc.

Dr. Mengjia Xu is currently a postdoc associate working at McGovern Institute for Brain Research, Center for Brains, Minds and Machines (CBMM) at MIT with Prof. Tomaso Poggio, and with Prof. George Karniadakis from the Division of Applied Mathematics at Brown University. Before joining MIT and Brown, she completed her PhD degree at the Department of Computer Science, Northeastern University (China) and two-year visiting PhD at Brown University. Her current research focuses on the optimization of deep neural networks, spatio-temporal graph representation learning, uncertainty quantification, and biomedical imaging data analysis for diverse applications.

...

Dr Xiaosheng Zhuang received his bachelor's degree and master's degree in mathematics from Sun Yat-Sen (Zhongshan) University, China, in 2003 and 2005, respectively. He received his PhD in applied mathematics from University of Alberta, Canada, in 2010. He was a Postdoctoral Fellow at Universität Osnabrück in 2011 and Technische Universität Berlin in 2012. His research interest includes directional multiscale representation systems, image/signal processing, and compressed sensing.

Prof Dongmian Zhou's primary research is in the intersection among applied harmonic analysis, machine learning and signal processing. He is especially interested in robust representations and structures in geometric and graph deep learning. His teaching interests at Duke Kunshan include calculus, linear algebra, principles of machine learning, statistical machine learning. He has had papers published in leading academic journals in various areas including Applied and Computational Harmonic Analysis and IEEE Transactions on Information Theory, and at and conferences such as the International Conference on Learning Representations.

He has a B.Sc. in mathematics from the Chinese University of Hong Kong and a Ph.D. in applied mathematics from the University of Maryland, College Park. Before joining Duke Kunshan, he served as a post-doctorate researcher at the University of Minnesota, Twin Cities.

Dr Xinliang Liu is a postdoc in KAUST. He is working on deep learning methods for numerical PDE and graph neural networks. He obtained his PhD in Mathematics from Shanghai Jiao Tong University.

Challenger is a theoretical physicist working on the long-standing problem of quantising gravity. Recently, he started to undertake work in Theoretical Machine Learning, in order to exploit its tools to understand String Theory as a problem in big data. As a Rhodes Scholar he has pursued his passion in understanding fundamental physical processes by undertaking doctoral work in String Theory at the Rudolf Peierls Centre for Theoretical Physics, University of Oxford. During his recently completed thesis, he worked on understanding various aspects of complex geometries that feature in String Theory, using the tools of differential and algebraic-geometry. Prior to this, Challenger completed his undergraduate work in Physics from the Indian Institute of Science Education and Research, Kolkata. During his undergraduate years, he worked on a NASA-sponsored project applying stochastic optimisation techniques to analyse data from the proposed gravitaional wave detector, LISA. When he isn’t tied up in stringy or machine learning affairs, he likes to show off his constantly diminishing skills in table tennis. After OATML, Challenger was appointed as an Accelerate Science Research Fellow at the University of Cambridge.

Jialin is PhD student in CS Department of Yale University, working on geometric deep learning and its applications. She is an undergraduate of Zhiyuan College at Shanghai Jiao Tong University with honours and outstanding thesis.