Active Labeling: Streaming Stochastic Gradients. (arXiv:2205.13255v1 [cs.LG])

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 generalizes
active learning based on partial supervision, we provide a streaming technique
that provably minimizes the ratio of generalization error over number of
samples. We illustrate …

arxiv labeling stochastic streaming