Don’t Label Twice: Quantity Beats Quality when Comparing Binary Classifiers on a Budget

2024

Conference Paper

sf

We study how to best spend a budget of noisy labels to compare the accuracy of two binary classifiers. It's common practice to collect and aggregate multiple noisy labels for a given data point into a less noisy label via a majority vote. We prove a theorem that runs counter to conventional wisdom. If the goal is to identify the better of two classifiers, we show it's best to spend the budget on collecting a single label for more samples. Our result follows from a non-trivial application of Cram\'er's theorem, a staple in the theory of large deviations. We discuss the implications of our work for the design of machine learning benchmarks, where they overturn some time-honored recommendations. In addition, our results provide sample size bounds superior to what follows from Hoeffding's bound.

@inproceedings{pmlr-v235-dorner24a,
  title = {Don't Label Twice: Quantity Beats Quality when Comparing Binary Classifiers on a Budget},
  author = {Dorner, Florian E. and Hardt, Moritz},
  booktitle = {Proceedings of the 41st International Conference on Machine Learning (ICML)},
  publisher = {PMLR},
  month = jul,
  year = {2024},
  doi = {},
  url = {https://proceedings.mlr.press/v235/dorner24a.html},
  month_numeric = {7}
}