Academic Lecture——Gaussian Process for Machine Learning: Overview, Recent Advances, and Outlook

Time: 9:00 a.m  Thursday, October 17, 2019
Place: Conference Room on the Third Floor in Electronic Information School
Speaker: Yin Feng      Chinese University of Hongkong(Shenzhen)

Abstract: Gaussian process (GP) for machine learning has been studied over the past two decades. GP models constitute a class of important Bayesian non-parametric models for machine learning has been studied over the past two decades. GP models constitute a class of important Bayesian non-parametric models for machine learning and tightly connect to several other salient models, such as support vector machines (SVM), single-layer Bayesian neural networks, regularized-least-squares, relevance vector machines and auto-regressive-moving-average (ARMA) model. GP models have been used in a plethora of applications due to their outstanding performance in function approximation with a natural uncertainty bound. GP models are also deemed as outstanding surrogate function in Bayesian optimization nowadays. In this seminar, I will first give an overview of the GP regression model, followed by some recent advances obtained on universal kernel design and low-cost GP regression model hyper-parameter optimization using the celebrated alternating direction method of multipliers (ADMM). Various applications of GP regression to distributed signal processing and wireless communication will be introduced at the end of the seminar.

Biography: Feng YIN is currently an assistant professor in the School of Science and Engineering at the Chinese University of Hong Kong, Shenzhen, China. He received the B.Sc. degree from Shanghai Jiao Tong University, China, in 2008, and the M.Sc. and Ph.D. degrees from Technische Universitaet Darmstadt, Germany, in 2011 and 2014, respectively. From 2014 to 2016, he was with Ericsson Research, Linkoping, Sweden, working on the European Union FP7 Marie Curie Training Programme on Tracking in Complex Sensor Systems (TRAX). Since 2016, he has been with The Chinese University of Hong Kong, Shenzhen and also affiliated with the Shenzhen Research Institute of Big Data (SRIBD). His research interests include statistical signal processing, Bayesian deep learning, and sensory data fusion. He was a recipient of the Chinese Government Award for Outstanding Self-Financed Students Abroad in 2013. He received the Marie Curie Scholarship from the European Union in 2014. He is currently serving as the handling editor of the Elsevier Signal Processing and Elsevier Digital Signal Processing.