|
Activity Number:
|
59
- Nonparametric Modeling
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Monday, August 3, 2020 : 10:00 AM to 2:00 PM
|
|
Sponsor:
|
Section on Nonparametric Statistics
|
|
Abstract #313299
|
|
|
Title:
|
Minimax Optimal Approaches to the Label Shift Problem
|
|
Author(s):
|
Subha Maity* and Yuekai Sun and Moulinath Banerjee
|
|
Companies:
|
University of Michigan and Dept of Statistics, University of Michigan, Ann Arbor and University of Michigan, Ann Arbor
|
|
Keywords:
|
Transfer Learning;
Label Shift
|
|
Abstract:
|
We study minimax rates of convergence in the label shift problem in non-parametric classification. In addition to the usual setting in which the learner only has access to unlabeled examples from the target domain, we also consider the setting in which a small number of labeled examples from the target domain is available to the learner. Our study reveals a difference in the difficulty of the label shift problem in the two settings. We attribute this difference to the availability of data from the target domain to estimate the class conditional distributions in the latter setting. We also show that a distributional matching approach is minimax rate-optimal in the former setting.
|
Authors who are presenting talks have a * after their name.
