Large Dimensional Asymptotics of Multi-Task Learning

Abstract

Multi Task Learning (MTL) efficiently leverages useful information contained in multiple related tasks to help improve the generalization performance of all tasks. This article conducts a large dimensional analysis of a simple but, as we shall see, extremely powerful when carefully tuned, Least Square Support Vector Machine (LSSVM) version of MTL, in the regime where the dimension p of the data and their number n grow large at the same rate. Under mild assumptions on the input data, the theoretical analysis of the MTL-LSSVM algorithm first reveals the "sufficient statistics" exploited by the algorithm and their interaction at work. These results demonstrate, as a striking consequence, that the standard approach to MTL-LSSVM is largely suboptimal, can lead to severe effects of negative transfer but that these impairments are easily corrected. These corrections are turned into an improved MTL-LSSVM algorithm which can only benefit from additional data, and the theoretical performance of which is also analyzed. As evidenced and theoretically sustained in numerous recent works, these large dimensional results are robust to broad ranges of data distributions, which our present experiments corroborate. Specifically, the article reports a systematically close behavior between theoretical and empirical performances on popular datasets, which is strongly suggestive of the applicability of the proposed carefully tuned MTL-LSSVM method to real data. This fine-tuning is fully based on the theoretical analysis and does not in particular require any cross validation procedure. Besides, the reported performances on real datasets almost systematically outperform much more elaborate and less intuitive state-of-the-art multi-task and transfer learning methods.

Large Dimensional Analysis of LS-SVM Transfer Learning: Application to Polsar Classification

“…Specifically, the article provides a theoretical analysis generalizing [4,5] to a data model with different covariance structures for each data class. As in [4,6], our analysis reveals the importance of optimizing the training data labels in order to combat negative transfer.…”

“…LS-SVM classification performances in high dimensions will heavily depend on the nature of the kernel function. This feature becomes adaptable to different given problem as explored in [9] and [6] for vanishing difference in means across classes.…”