Marginal Singularity, and the Benefits of Labels in Covariate-Shift
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.
Code (0)
등록된 구현이 없습니다.
Tasks
General ClassificationSimilar Papers 제목 키워드 기반
The Power and Limitation of Pretraining-Finetuning for Linear Regression under Covariate Shift
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 LearningFlexible Transfer Learning under Support and Model Shift
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 LearningEstimating and Explaining Model Performance When Both Covariates and Labels Shift
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
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
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