Active Labeling: Streaming Stochastic Gradients

Vivien Cabannes, Francis Bach, Vianney Perchet, Alessandro Rudi

Keywords: Weak supervision, partial labeling, active learning, sgd

TL;DR: Active weakly supervised learning based on partial labeling

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.

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2205.13255/code)