paper-with-me

홈 › Papers

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

2018-03-05 · Samory Kpotufe, Guillaume Martinet

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 $\gamma$ 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 $\gamma$ - 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 $\gamma$, and therefore requests labels only when beneficial, while achieving minimax transfer rates.

📄 PDF Abstract BibTeX arXiv:1803.01833

Code (0)

등록된 구현이 없습니다.

Tasks

General Classification

Similar Papers 제목 키워드 기반

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

2022-08-03 · Jingfeng Wu, Difan Zou, Vladimir Braverman, Quanquan Gu 외

We study linear regression under covariate shift, where the marginal distribution over the input covariates differs in the source and the target domains, while the conditional distribution of the output given the input c…

regressionTransfer Learning

Flexible Transfer Learning under Support and Model Shift

2014-12-01 · NeurIPS 2014 12 · Xuezhi Wang, Jeff Schneider

Transfer learning algorithms are used when one has sufficient training data for one supervised learning task (the source/training domain) but only very limited training data for a second task (the target/test domain) tha…

Transfer Learning

Estimating and Explaining Model Performance When Both Covariates and Labels Shift

2022-09-18 · Lingjiao Chen, Matei Zaharia, James Zou

Deployed machine learning (ML) models often encounter new user data that differs from their training data. Therefore, estimating how well a given model might perform on the new data is an important step toward reliable M…

Robust Covariate Shift Prediction with General Losses and Feature Views

2017-12-28 · Anqi Liu, Brian D. Ziebart

Covariate shift relaxes the widely-employed independent and identically distributed (IID) assumption by allowing different training and testing input distributions. Unfortunately, common methods for addressing covariate …

Rethinking the Evaluation of Out-of-Distribution Detection: A Sorites Paradox

2024-06-14 · Xingming Long, Jie Zhang, Shiguang Shan, Xilin Chen

Most existing out-of-distribution (OOD) detection benchmarks classify samples with novel labels as the OOD data. However, some marginal OOD samples actually have close semantic contents to the in-distribution (ID) sample…

Out-of-Distribution DetectionOut of Distribution (OOD) Detection