Multi-Task Classification Hypothesis Space with Improved Generalization Bounds

2013/12/09 by Cong Li, Li, Cong, Michael Georgiopoulos +3 · 1 citation
Computer Science · Engineering · #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning and ELM #Sparse and Compressive Sensing Techniques

paper · pdf · doi:10.48550/arxiv.1312.2606

openalex publication_date 2013/12/09 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

This paper presents a RKHS, in general, of vector-valued functions intended to be used as hypothesis space for multi-task classification. It extends similar hypothesis spaces that have previously considered in the literature. Assuming this space, an improved Empirical Rademacher Complexity-based generalization bound is derived. The analysis is itself extended to an MKL setting. The connection between the proposed hypothesis space and a Group-Lasso type regularizer is discussed. Finally, experimental results, with some SVM-based Multi-Task Learning problems, underline the quality of the derived bounds and validate the paper's analysis.

Cited by

• Collaborative Management for Chronic Diseases and Depression: A Double Heterogeneity-based Multi-Task Learning Method

Related

• Task-group Relatedness and Generalization Bounds for Regularized Multi-task Learning
• Learning Rates for Multi-task Regularization Networks
• Multi-Task Learning with Group-Specific Feature Space Sharing
• Multi-Task Regularization with Covariance Dictionary for Linear Classifiers
• Multi-Task Learning Using Neighborhood Kernels