Adaptive and robust multi-task learning
Date: Thursday, 3 March 2022
Time: 10 am - 11 am
Speaker: Associate Professor Kaizheng Wang
Abstract:
In this talk we study the multi-task learning problem that aims to simultaneously analyze multiple datasets collected from different sources and learn one model for each of them. We propose a family of adaptive methods that automatically utilize possible similarities among those tasks while carefully handling their differences. We derive optimal statistical guarantees for the methods and prove their robustness against outlier tasks. Numerical experiments on synthetic and real datasets demonstrate the efficacy of our new methods. The talk is based on joint work with Yaqi Duan.
Zoom Link: Please contact Yanrong Yang (yanrong.yang@anu.edu.au) to obtain the zoom link for this seminar.