The great success of large deep learning models in various applications in recent years have encouraged many researchers to seek improved performance by utilizing larger models and bigger data in practical problems involving unstructured data, leading to psychological implications to pursuit large models everywhere. However, the fundamental principle of statistical modeling tells us that an over-flexible large model without a clear focus on unique features of the problem of interest would often lead to inefficient utilization of data and sub-optimal results. In this talk, I will provide a few examples in analyzing complex unstructured data, including texts, videos and multimodal data, that deep learning can be greatly enhanced by statical learning once we integrate them wisely. We hope these examples could inspire more research efforts on developing advanced statistical approaches with competitive performance and transparent interpretation for analyzing complex unstructured data on top of deep learning.

Speaker Biography:Deng Ke, Associate Professor and Deputy Head of the Department of Statistics and Data Science at Tsinghua University, and Vice Dean of the Interdisciplinary Research Institute for Data Science at Tsinghua University. Mainly engaged in research on Bayesian statistical methods and interdisciplinary research with biomedical, artificial intelligence, intelligent manufacturing, humanities and social sciences. In 2008, he obtained a PhD in Statistics from Peking University and entered the Department of Statistics at Harvard University to conduct research. He has served as a postdoctoral fellow and associate researcher, and has been working at Tsinghua University since 2013. In 2014, he was selected for the Youth Program of the National High level Talent Plan. In 2016, he was honored with the title of "Scientific Chinese Person of the Year". In 2018, he was employed as a "Zhiyuan Researcher" in the field of mathematical foundations at Beijing Zhiyuan Artificial Intelligence Research Institute. In 2024, he was elected as an Elected Member of the International Statistical Institute (ISI). Published over 50 papers in renowned journals and conferences in statistics and data science, and led multiple key research and development programs of the Ministry of Science and Technology, National Natural Science Foundation, National Social Science Foundation, and Beijing Natural Science Foundation projects. The research work in Chinese text analysis and digital humanities has won the Best Paper Award at the International Conference of Chinese Mathematicians (ICCM) and the China Digital Humanities Conference. The research work in bioinformatics has won the Natural Science Award of the Ministry of Education for Excellent Achievements in University Science Research. Multiple achievements in government big data analysis have been adopted and applied by the government. He is a member of the Asia Pacific Branch of the International Society for Computational Statistics, the Chairman of the Computational Statistics Branch of the China Association for On site Statistics, the Vice President of the China Association of Young Statisticians, the Vice Chairman of the Smart Healthcare Professional Committee of the Chinese Association for Artificial Intelligence, a member of the National Expert Committee on Clinical Application of Anti tumor Drugs, and also serves as the Deputy Editor in Chief of the international statistical journals Statistica Sinica and Communications in Statistics, as well as an editorial board member of journals such as Applied Probability Statistics, Applied Mathematics and Mechanics, Statistics and Actuarial Science, and Digital Humanities.