Active Labeling: Streaming Stochastic Gradients
Machine Learning
2022-12-08 v3 Artificial Intelligence
Information Retrieval
Machine Learning
Abstract
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.
Cite
@article{arxiv.2205.13255,
title = {Active Labeling: Streaming Stochastic Gradients},
author = {Vivien Cabannes and Francis Bach and Vianney Perchet and Alessandro Rudi},
journal= {arXiv preprint arXiv:2205.13255},
year = {2022}
}
Comments
38 pages (9 main pages), 9 figures