Transfer Learning: Optimality and Adaptive Algorithms

Tony Cai (University of Pennsylvania)

Human learners have the natural ability to use knowledge gained in one setting for learning in a different but related setting. This ability to transfer knowledge from one task to another is essential for effective learning. However, in statistical learning, most procedures are designed to solve one single task, or to learn one single distribution, based on observations from the same setting.

In this talk, we discuss statistical transfer learning in various settings with a focus on nonparametric classification based on observations from different distributions under the posterior drift model, which is a general framework and arises in many practical problems. The results show that significant benefit of incorporating data from the source distributions for learning under the target distribution.


Back to Day 3