Marginal Singularity, and the Benefits of Labels in Covariate-Shift

03/05/2018
by   Samory Kpotufe, et al.
0

We present new minimax results that concisely capture the relative benefits of source and target labeled data, under covariate-shift. Namely, we show that the benefits of target labels are controlled by a transfer-exponent γ that encodes how singular Q is locally w.r.t. P, and interestingly allows situations where transfer did not seem possible under previous insights. In fact, our new minimax analysis - in terms of γ - reveals a continuum of regimes ranging from situations where target labels have little benefit, to regimes where target labels dramatically improve classification. We then show that a recently proposed semi-supervised procedure can be extended to adapt to unknown γ, and therefore requests labels only when beneficial, while achieving minimax transfer rates.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/06/2022

A new similarity measure for covariate shift with applications to nonparametric regression

We study covariate shift in the context of nonparametric regression. We ...
research
08/03/2022

The Power and Limitation of Pretraining-Finetuning for Linear Regression under Covariate Shift

We study linear regression under covariate shift, where the marginal dis...
research
05/07/2023

Classification Tree Pruning Under Covariate Shift

We consider the problem of pruning a classification tree, that is, selec...
research
03/29/2023

Sparse joint shift in multinomial classification

Sparse joint shift (SJS) was recently proposed as a tractable model for ...
research
02/20/2023

Pseudo-Labeling for Kernel Ridge Regression under Covariate Shift

We develop and analyze a principled approach to kernel ridge regression ...
research
06/08/2021

Adaptive transfer learning

In transfer learning, we wish to make inference about a target populatio...
research
01/27/2020

A Primer on Domain Adaptation

Standard supervised machine learning assumes that the distribution of th...

Please sign up or login with your details

Forgot password? Click here to reset