I recognize that interdisciplinary research offers greater opportunities for scientific and technological breakthroughs since the world is diverse and statistics/biostatistics alone can not address all problems in isolation.
My research interest lies in the intersection of machine learning and statistics. My general focus is to apply machine learning techniques to improve traditional statistical methodologies/overcome the existing bottleneck of statistical procedures and introduce statistical ideas in machine learning. Currently, I’m focused on developing non-computationally intensive matrix factorisation techniques and applying these techniques to solve practical problems. Additionally, I’m also interested in protecting each individual’s privacy when analyzing sample data, especially the differential privacy technique where statistical random errors are added when sharing information about a dataset. I have actively collaborated with professors in both statistics and electrical engineering as well as industry, such as the Huawei company in Canada and Hong Kong.
My research area also includes Reinforcement Learning, High Dimensional Data, Bridging Study, Functional Data Analysis, Biostatistics, Semiparametric Modelling, Causal Inference, and Rank Estimation.
2023, Professor Feipeng Zhang, School of Finance and Economics, Xi’an Jiaotong University, Xi’an, China (27 Mar – 25 May)
2023, Mr Bo Pan, Biostatistician, Epidemiology Coordinating and Research (EPICORE) Centre, University of Alberta, Edmonton, Canada
2023, Dr Yafei Wang, Lecturer in Statistics, Department of Mathematical Sciences, University of Essex, Colchester, United Kingdom
2022, Research and Innovation Fund, Division of Computing, Engineering, and Mathematical Sciences, University of Kent
2023, UK Research and Innovation General Funds, UKRI
2023, Improving the statistical analysis of brain imaging data to generate more accurate descriptions of brain activity, UK Research and Innovation, Knowledge Transfer Partnerships (KTP) Fund
2023, Federated Learning based Quantile Regression Model for Credit Card Fraud Detection, Cyber Security Seedcorn Funding, Institute of Cyber Security for Society, University of Kent