Adaptive and Robust Multi-task Learning

02/10/2022
by   Yaqi Duan, et al.
0

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 sharp 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.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset