The workhorse of machine learning is stochastic gradient descent. To access stochastic gradients, it is common to consider iteratively input/output pairs of a training dataset. Interestingly, it appears that one does not need full supervision to access stochastic gradients, which is the main motivation of this paper. After formalizing the "active labeling" problem, which focuses on active learning with partial supervision, we provide a streaming technique that provably minimizes the ratio of generalization error over the number of samples. We illustrate our technique in depth for robust regression.
翻译:机器学习的工作马是随机梯度下降。 要访问随机梯度, 通常会考虑培训数据集的迭代输入/ 输出对。 有趣的是, 似乎不需要全面监督来访问随机梯度, 而这是本文的主要动机。 在正式解决“ 主动标签” 问题( 重点是以部分监督进行积极学习) 之后, 我们提供一种流学技术, 以可以将样本数量中的一般错误比例降到最低。 我们用深度来说明我们如何进行强力回归。