论文标题
自适应和强大的多任务学习
Adaptive and Robust Multi-Task Learning
论文作者
论文摘要
我们研究了多任务学习问题，该问题旨在同时分析从不同来源收集的多个数据集，并为每个数据集学习一个模型。我们提出了一个自适应方法家族，该家族在仔细处理其差异的同时，自动利用这些任务之间可能的相似性。我们为这些方法提供了敏锐的统计保证，并证明了它们针对异常任务的鲁棒性。关于合成和实际数据集的数值实验证明了我们新方法的功效。
We study the multi-task learning problem that aims to simultaneously analyze multiple datasets collected from different sources and learn one model for each of them. We propose a family of adaptive methods that automatically utilize possible similarities among those tasks while carefully handling their differences. We derive sharp statistical guarantees for the methods and prove their robustness against outlier tasks. Numerical experiments on synthetic and real datasets demonstrate the efficacy of our new methods.
