论文标题
adatask：自适应多任务在线学习
AdaTask: Adaptive Multitask Online Learning
论文作者
论文摘要
我们介绍和分析Adatask，这是一种适应任务未知结构的多任务在线学习算法。当$ n $任务被随机激活时，我们表明，adatask的遗憾比一个可以大于$ \ sqrt {n} $大的因素要比运行$ n $ n $独立算法所获得的遗憾，而对于每个任务。 Adatask可以看作是具有Mahalanobis Norm潜力的跟随定制领导者的比较器自适应版本。通过对这种潜力的各种表述，我们的分析揭示了Adatask如何共同学习任务及其结构。提出了支持我们发现的实验。
We introduce and analyze AdaTask, a multitask online learning algorithm that adapts to the unknown structure of the tasks. When the $N$ tasks are stochastically activated, we show that the regret of AdaTask is better, by a factor that can be as large as $\sqrt{N}$, than the regret achieved by running $N$ independent algorithms, one for each task. AdaTask can be seen as a comparator-adaptive version of Follow-the-Regularized-Leader with a Mahalanobis norm potential. Through a variational formulation of this potential, our analysis reveals how AdaTask jointly learns the tasks and their structure. Experiments supporting our findings are presented.
