Efficient Learning with Arbitrary Covariate Shift
We give an efficient algorithm for learning a binary function in a given class C of bounded VC dimension, with training data distributed according to P and test data according to Q, where P and Q may be arbitrary distributions over X. This is the generic form of what is called covariate shift, which is impossible in general as arbitrary P and Q may not even overlap. However, recently guarantees were given in a model called PQ-learning (Goldwasser et al., 2020) where the learner has: (a) access to unlabeled test examples from Q (in addition to labeled samples from P, i.e., semi-supervised learning); and (b) the option to reject any example and abstain from classifying it (i.e., selective classification). The algorithm of Goldwasser et al. (2020) requires an (agnostic) noise tolerant learner for C. The present work gives a polynomial-time PQ-learning algorithm that uses an oracle to a "reliable" learner for C, where reliable learning (Kalai et al., 2012) is a model of learning with one-sided noise. Furthermore, our reduction is optimal in the sense that we show the equivalence of reliable and PQ learning.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
High-Dimensional Kernel Methods under Covariate Shift: Data-Dependent Implicit Regularization
This paper studies kernel ridge regression in high dimensions under covariate shifts and analyzes the role of importance re-weighting. We first derive the asymptotic expansion of high dimensional kernels under covariate …
FOOGD: Federated Collaboration for Both Out-of-distribution Generalization and Detection
Federated learning (FL) is a promising machine learning paradigm that collaborates with client models to capture global knowledge. However, deploying FL models in real-world scenarios remains unreliable due to the coexis…
Federated LearningOut-of-Distribution GeneralizationBeyond the Training Distribution: Evaluating Predictions Under Distribution Shift and Selection Bias
Understanding how a prediction model will perform in a new environment before deployment is essential to preventing harm when algorithms inform decision-making. Two common sources of model performance degradation are (i)…
Self-organizing interval type-2 fuzzy neural network with adaptive discriminative strategy
Covariate shift is a critical issue of interval type-2 fuzzy neural networks (IT2FNNs) due to the distribution discrepancy between training and testing samples. In this situation, IT2FNNs usually struggle to identify pot…
Joint covariate-alignment and concept-alignment: a framework for domain generalization
In this paper, we propose a novel domain generalization (DG) framework based on a new upper bound to the risk on the unseen domain. Particularly, our framework proposes to jointly minimize both the covariate-shift as wel…
Concept AlignmentDomain Generalization