论文标题
弱点的力量：使用弱监督的快速学习
Strength from Weakness: Fast Learning Using Weak Supervision
论文作者
论文摘要
我们研究弱监督学习的概括属性。也就是说，学习只有少数“强”标签（我们预测的实际目标），但是可以使用更多的“弱”标签。特别是，我们表明，访问弱标签可以大大加速强大任务的学习率，以达到$ \ Mathcal {o}（\ nicefrac1n）$的快速率，其中$ n $表示标记的数据点的数量。即使按照强标记的数据本身仅接受较慢的$ \ MATHCAL {O}（\ nicefrac {1} {\ sqrt {n}}）$ rate，也可能发生这种加速度。实际加速度不断取决于可用的弱标签数量以及两个任务之间的关系。我们的理论结果在一系列任务中经验反映，并说明了弱标签如何加快学习强大任务的学习。
We study generalization properties of weakly supervised learning. That is, learning where only a few "strong" labels (the actual target of our prediction) are present but many more "weak" labels are available. In particular, we show that having access to weak labels can significantly accelerate the learning rate for the strong task to the fast rate of $\mathcal{O}(\nicefrac1n)$, where $n$ denotes the number of strongly labeled data points. This acceleration can happen even if by itself the strongly labeled data admits only the slower $\mathcal{O}(\nicefrac{1}{\sqrt{n}})$ rate. The actual acceleration depends continuously on the number of weak labels available, and on the relation between the two tasks. Our theoretical results are reflected empirically across a range of tasks and illustrate how weak labels speed up learning on the strong task.
