Active Labeling: Streaming Stochastic Gradients

Vivien Cabannes; Francis Bach; Vianney Perchet; Alessandro Rudi

NeurIPS 2022accept2 citations

Active Labeling: Streaming Stochastic Gradients

Vivien Cabannes, Francis Bach, Vianney Perchet, Alessandro Rudi

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.

Weak supervisionpartial labelingactive learningsgd

BibTeX

@inproceedings{
cabannes2022active,
title={Active Labeling: Streaming Stochastic Gradients},
author={Vivien Cabannes and Francis Bach and Vianney Perchet and Alessandro Rudi},
booktitle={Advances in Neural Information Processing Systems},
editor={Alice H. Oh and Alekh Agarwal and Danielle Belgrave and Kyunghyun Cho},
year={2022},
url={https://openreview.net/forum?id=Iqm6AiHPs_z}
}