A Generalization Error Bound for Multi-class Domain Generalization

Abstract

Domain generalization is the problem of assigning labels to an unlabeled data set, given several similar data sets for which labels have been provided. Despite considerable interest in this problem over the last decade, there has been no theoretical analysis in the setting of multi-class classification. In this work, we study a kernel-based learning algorithm and establish a generalization error bound that scales logarithmically in the number of classes, matching state-of-the-art bounds for multi-class classification in the conventional learning setting. We also demonstrate empirically that the proposed algorithm achieves significant performance gains compared to a pooling strategy.

References in corpus (3)

• Multi-class SVMs: From Tighter Data-Dependent Generalization Bounds to Novel Algorithms
• Structured Prediction Theory Based on Factor Graph Complexity
• Convex Calibration Dimension for Multiclass Loss Matrices

Cited by in corpus (8)

• Domain Generalization: A Survey
• Towards Out-Of-Distribution Generalization: A Survey
• In Search of Lost Domain Generalization
• Towards a Theoretical Framework of Out-of-Distribution Generalization
• Model-Based Domain Generalization
• Offline RL With Resource Constrained Online Deployment
• Explainability-aided Domain Generalization for Image Classification
• Discriminative Domain-Invariant Adversarial Network for Deep Domain Generalization