• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>16th Annual Conference on Learning Theory and 7th Kernel Workshop, COLT/Kernel 2003 Aug 24-27, 2003 Washington, DC, USA >Exploiting Task Relatedness for Multiple Task Learning
【24h】

Exploiting Task Relatedness for Multiple Task Learning

机译：利用任务相关性进行多任务学习

获取原文
获取原文并翻译 | 示例
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

The approach of learning of multiple "related" tasks simultaneously has proven quite successful in practice; however, theoretical justification for this success has remained elusive. The starting point for previous work on multiple task learning has been that the tasks to be learned jointly are somehow "algorithmically related", in the sense that the results of applying a specific learning algorithm to these tasks are assumed to be similar. We offer an alternative approach, defining relat-edness of tasks on the basis of similarity between the example generating distributions that underline these task. We provide a formal framework for this notion of task relatedness, which captures a sub-domain of the wide scope of issues in which one may apply a multiple task learning approach. Our notion of task similarity is relevant to a variety of real life multitask learning scenarios and allows the formal derivation of generalization bounds that are strictly stronger than the previously known bounds for both the learning-to-learn and the multitask learning scenarios. We give precise conditions under which our bounds guarantee generalization on the basis of smaller sample sizes than the standard single-task approach.
机译：实践证明，同时学习多个“相关”任务的方法非常成功。然而，这种成功的理论依据仍然难以捉摸。从以前的工作出发，多任务学习的出发点是，要共同学习的任务在某种意义上是“算法上相关的”，从某种意义上讲，将特定学习算法应用于这些任务的结果被认为是相似的。我们提供了一种替代方法，即根据示例生成这些任务的分布之间的相似性来定义任务的相关性。我们为任务相关性的概念提供了一个正式的框架，该框架涵盖了广泛问题的一个子领域，在其中可以应用多种任务学习方法。我们的任务相似性概念与现实生活中的各种多任务学习场景有关，并且允许正式推导泛化范围，该范围比学习学习和多任务学习场景中的已知范围严格更强。我们给出了精确的条件，在这些条件下，我们的界限可以保证比标准的单任务方法更小样本量。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号