English

Efficacy of regularized multi-task learning based on SVM models

Machine Learning 2022-02-22 v2 Machine Learning

Abstract

This paper investigates the efficacy of a regularized multi-task learning (MTL) framework based on SVM (M-SVM) to answer whether MTL always provides reliable results and how MTL outperforms independent learning. We first find that M-SVM is Bayes risk consistent in the limit of large sample size. This implies that despite the task dissimilarities, M-SVM always produces a reliable decision rule for each task in terms of misclassification error when the data size is large enough. Furthermore, we find that the task-interaction vanishes as the data size goes to infinity, and the convergence rates of M-SVM and its single-task counterpart have the same upper bound. The former suggests that M-SVM cannot improve the limit classifier's performance; based on the latter, we conjecture that the optimal convergence rate is not improved when the task number is fixed. As a novel insight of MTL, our theoretical and experimental results achieved an excellent agreement that the benefit of the MTL methods lies in the improvement of the pre-convergence-rate factor (PCR, to be denoted in Section III) rather than the convergence rate. Moreover, this improvement of PCR factors is more significant when the data size is small.

Keywords

Cite

@article{arxiv.1805.12507,
  title  = {Efficacy of regularized multi-task learning based on SVM models},
  author = {Shaohan Chen and Zhou Fang and Sijie Lu and Chuanhou Gao},
  journal= {arXiv preprint arXiv:1805.12507},
  year   = {2022}
}

Comments

12 pages, 4 figures

R2 v1 2026-06-23T02:14:50.040Z