[CFAR Rising Star Lecture Series]
Nearest Neighbor Methods with Applications in Functional Estimation and Machine Learning by Dr Zhao Puning
30 Jun 2022 | 10:00am (Singapore Time)
K-Nearest Neighbors (kNN) is an important non-parametric statistical method, which is widely applied in many areas, such as functional estimation, density estimation and machine learning. Despite it’s popularity, some theoretical properties are still not well understood.
In this talk, Dr Zhao Puning will focus on three problems: 1) Estimation of entropy and mutual information; 2) Estimation of KL divergence; and 3) Minimax optimal adaptive classification and regression. For all of these problems, Dr Zhao will first derive the theoretical bound of the performance of the kNN method, and then derive the theoretical minimax lower bound of all methods using information theoretic approaches. Finally, he will talk about improvement on the traditional kNN method if the upper bound does not match the lower limit.
Dr Zhao Puning graduated from University of Science and Technology of China (USTC) in 2017 with a B.S. degree. He then graduated from University of California, Davis (UCD) with a PhD in Electrical Engineering. He is currently working in Tencent Holdings Limited. His research interests include statistical learning and information theory.