Exploiting task relatedness for multiple task learning
Exploiting task relatedness for multiple task learning
复制标题
DOI：
10.1007/978-3-540-45167-9_41
复制
发表时间：
2003-01-01
期刊：
影响因子：
--
通讯作者：
Schuller, R
中科院分区：
文献类型：
--
作者：
Ben-David, S;Schuller, R
同时学习多个“相关”任务的方法在实践中已证明很成功。但是，这一成功的理论理由仍然难以捉摸。先前在多个任务学习的工作的起点是，共同学习的任务在某种程度上是“算法相关的”，因为将特定的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，根据示例生成强调这些任务的示例之间的相似性来定义任务的相关性。我们为这一任务相关性的概念提供了一个正式的框架，该框架捕获了广泛问题的子域，哪一种可能采用多种任务学习方法。我们的任务相似性概念与各种现实生活中的多任务学习方案有关，并允许正式推导概括性界限，这些范围比学习对学习和多任务学习方案的先前已知界限要严格强。我们给出确切的条件，在这些条件下，我们的界限比标准单任务方法更小的样本量确保概括。
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 relatedness 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.