The Label Complexity of Mixed-Initiative Classifier Training

@inproceedings{Suh2016TheLC,
  title={The Label Complexity of Mixed-Initiative Classifier Training},
  author={Jina Suh and Xiaojin Zhu and Saleema Amershi},
  booktitle={ICML},
  year={2016}
}
Mixed-initiative classifier training, where the human teacher can choose which items to label or to label items chosen by the computer, has enjoyed empirical success but without a rigorous statistical learning theoretical justification. We analyze the label complexity of a simple mixed-initiative training mechanism using teaching dimension and active learning. We show that mixed-initiative training is advantageous compared to either computer-initiated (represented by active learning) or human… CONTINUE READING

5 Figures & Tables

Topics

Statistics

01020201620172018
Citations per Year

Citation Velocity: 6

Averaging 6 citations per year over the last 3 years.

Learn more about how we calculate this metric in our FAQ.