Consistent Multitask Learning with Nonlinear Output Relations
Consistent Multitask Learning with Nonlinear Output Relations
复制标题
DOI：
--
复制
发表时间：
2017-05
期刊：
影响因子：
--
通讯作者：
C. Ciliberto;Alessandro Rudi;L. Rosasco;M. Pontil
中科院分区：
文献类型：
--
作者：
C. Ciliberto;Alessandro Rudi;L. Rosasco;M. Pontil
多任务学习的关键是利用不同任务之间的关系来提高预测性能。如果这些关系是线性的，则可以成功地使用正则化方法。然而，在实践中，假设这些任务是线性相关的可能是有限制的，并且考虑到非线性结构是一个挑战。在本文中，我们通过把这个问题放在结构化预测的框架内来解决这个问题。我们的主要贡献是提出了一种新的算法来学习多个任务，这些任务由一个非线性方程系统联系在一起，它们的联合输出需要满足。我们证明了该算法是一致的，并且可以有效地实现。实验结果表明了该方法的有效性。
Key to multitask learning is exploiting relationships between different tasks to improve prediction performance. If the relations are linear, regularization approaches can be used successfully. However, in practice assuming the tasks to be linearly related might be restrictive, and allowing for nonlinear structures is a challenge. In this paper, we tackle this issue by casting the problem within the framework of structured prediction. Our main contribution is a novel algorithm for learning multiple tasks which are related by a system of nonlinear equations that their joint outputs need to satisfy. We show that the algorithm is consistent and can be efficiently implemented. Experimental results show the potential of the proposed method.