A theory of learning from different domains

DOI10.1007/s10994-009-5152-4zbMath1470.68081OpenAlexW2104094955WikidataQ63199026 ScholiaQ63199026MaRDI QIDQ1959571

Publication date: 7 October 2010

Published in: Machine Learning (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s10994-009-5152-4

zbMATH Keywords

learning theory transfer learning domain adaptation sample-selection bias

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Learning and adaptive systems in artificial intelligence (68T05)

Related Items (45)

Learning models with uniform performance via distributionally robust optimization ⋮ Fast rates by transferring from auxiliary hypotheses ⋮ Semantic Image Segmentation: Two Decades of Research ⋮ PAC-Bayesian lifelong learning for multi-armed bandits ⋮ Interpretable domain adaptation via optimization over the Stiefel manifold ⋮ The Out-of-Source Error in Multi-Source Cross Validation-Type Procedures ⋮ Improved linear regression prediction by transfer learning ⋮ A kernel learning framework for domain adaptation learning ⋮ Communication-efficient distributed multi-task learning with matrix sparsity regularization ⋮ On the benefits of representation regularization in invariance based domain generalization ⋮ Self-supervised segmentation using synthetic datasets via L-system ⋮ A Bayesian approach to (online) transfer learning: theory and algorithms ⋮ Reducing bias to source samples for unsupervised domain adaptation ⋮ Estimating the Area under the ROC Curve When Transporting a Prediction Model to a Target Population ⋮ KS(conf): a light-weight test if a multiclass classifier operates outside of its specifications ⋮ Adaptive distribution calibration for few-shot learning via optimal transport ⋮ Unnamed Item ⋮ Domain adversarial neural networks for domain generalization: when it works and how to improve ⋮ MapFlow: latent transition via normalizing flow for unsupervised domain adaptation ⋮ NaCL: noise-robust cross-domain contrastive learning for unsupervised domain adaptation ⋮ Unsupervised semantic-aware adaptive feature fusion network for arrhythmia detection ⋮ Learning kernels for unsupervised domain adaptation with applications to visual object recognition ⋮ Model-driven domain adaptation on product manifolds for unconstrained face recognition ⋮ Error controlled actor-critic ⋮ A theoretical framework for deep transfer learning ⋮ Robust unsupervised domain adaptation for neural networks via moment alignment ⋮ Relative deviation learning bounds and generalization with unbounded loss functions ⋮ Multi-domain learning by confidence-weighted parameter combination ⋮ A theory of learning from different domains ⋮ Mismatched Training and Test Distributions Can Outperform Matched Ones ⋮ Adversarial domain adaptation network for tumor image diagnosis ⋮ Robust domain adaptation ⋮ On generalization in moment-based domain adaptation ⋮ Learning smooth representations with generalized softmax for unsupervised domain adaptation ⋮ Unsupervised domain adaptation in the wild via disentangling representation learning ⋮ Unnamed Item ⋮ Unsupervised domain adaptation with non-stochastic missing data ⋮ Marginal singularity and the benefits of labels in covariate-shift ⋮ Adaptive transfer learning ⋮ Nuclear discrepancy for single-shot batch active learning ⋮ On the analysis of adaptability in multi-source domain adaptation ⋮ Intentional Control of Type I Error Over Unconscious Data Distortion: A Neyman–Pearson Approach to Text Classification ⋮ Unnamed Item ⋮ Statistical learning from biased training samples ⋮ A no-free-lunch theorem for multitask learning

Cites Work

This page was built for publication: A theory of learning from different domains