Abstract: We present a family of pairwise tournaments reducing k-class classification to binary classification. These reductions are provably robust against a constant fraction of binary errors, and match the best possible computation and regret up to a constant.
Download: pdf, arXiv version
Citation
- Error-Correcting Tournaments (pdf, arXiv, software)
A. Beygelzimer, J. Langford, P. Ravikumar.
In International Conference on Algorithmic Learning Theory (ALT), 2009.
Bibtex: