Efficient and Provable Algorithms for Covariate Shift
Covariate shift, a widely used assumption in tackling {\it distributional shift} (when training and test distributions differ), focuses on scenarios where the distribution of the labels conditioned on the feature vector is the same, but the distribution of features in the training and test data are different. Despite the significance and extensive work on covariate shift, theoretical guarantees for algorithms in this domain remain sparse. In this paper, we distill the essence of the covariate shift problem and focus on estimating the average $\mathbb{E}_{\tilde{\mathbf{x}}\sim p_{\mathrm{test}}}\mathbf{f}(\tilde{\mathbf{x}})$, of any unknown and bounded function $\mathbf{f}$, given labeled training samples $(\mathbf{x}_i, \mathbf{f}(\mathbf{x}_i))$, and unlabeled test samples $\tilde{\mathbf{x}}_i$; this is a core subroutine for several widely studied learning problems. We give several efficient algorithms, with provable sample complexity and computational guarantees. Moreover, we provide the first rigorous analysis of algorithms in this space when $\mathbf{f}$ is unrestricted, laying the groundwork for developing a solid theoretical foundation for covariate shift problems.
Code (0)
등록된 구현이 없습니다.
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
A Theoretical Analysis on Independence-driven Importance Weighting for Covariate-shift Generalization
Covariate-shift generalization, a typical case in out-of-distribution (OOD) generalization, requires a good performance on the unknown test distribution, which varies from the accessible training distribution in the form…
feature selectionImageNet-OOD: Deciphering Modern Out-of-Distribution Detection Algorithms
The task of out-of-distribution (OOD) detection is notoriously ill-defined. Earlier works focused on new-class detection, aiming to identify label-altering data distribution shifts, also known as "semantic shift." Howeve…
Out-of-Distribution DetectionOut of Distribution (OOD) DetectionSemantic Shift DetectionContrastive Identification of Covariate Shift in Image Data
Identifying covariate shift is crucial for making machine learning systems robust in the real world and for detecting training data biases that are not reflected in test data. However, detecting covariate shift is challe…
AttributeEstimating Continuous Treatment Effects with Two-Stage Kernel Ridge Regression
We study the problem of estimating the effect function for a continuous treatment, which maps each treatment value to a population-averaged outcome. A central challenge in this setting is confounding: treatment assignmen…
Explaining Predictive Uncertainty with Information Theoretic Shapley Values
Researchers in explainable artificial intelligence have developed numerous methods for helping users understand the predictions of complex supervised learning models. By contrast, explaining the $\textit{uncertainty}$ of…
Active LearningDecision Making Under UncertaintyDepth Aleatoric Uncertainty EstimationExplainable Artificial Intelligence (XAI)+1