Abstract: In this talk, Kaizheng Wang will present a versatile framework for statistical learning in non-stationary environments. In each time period, their approach applies a stability principle to select a look-back window that maximizes the utilization of historical data while keeping the cumulative bias within an acceptable range relative to the stochastic error. Their theory showcases the adaptability of this approach to unknown non-stationarity. The regret bound is minimax optimal up to logarithmic factors when the population losses are strongly convex, or Lipschitz only. At the heart of our analysis lie two novel components: a measure of similarity between functions and a segmentation technique for dividing the non-stationary data sequence into quasi-stationary pieces. The talk is based on joint work with Chengpiao Huang.

Bio: Kaizheng Wang is an assistant professor of Industrial Engineering and Operations Research, and a member of the Data Science Institute at Columbia University. He works at the intersection of machine learning, optimization and statistics. He received the SIAM Activity Group on Imaging Science Best Paper Prize in 2024, and the Second Place Award in the 2023 INFORMS Data Mining Challenge. He obtained his PhD from Princeton University in 2020 and BS from Peking University in 2015.

This event is part of the IOE Departmental Seminar Series