arXiv Open Access 2017

On conditional parity as a notion of non-discrimination in machine learning

Ya'acov Ritov Yuekai Sun Ruofei Zhao

Lihat Sumber

Abstrak

We identify conditional parity as a general notion of non-discrimination in machine learning. In fact, several recently proposed notions of non-discrimination, including a few counterfactual notions, are instances of conditional parity. We show that conditional parity is amenable to statistical analysis by studying randomization as a general mechanism for achieving conditional parity and a kernel-based test of conditional parity.

Topik & Kata Kunci

stat.ML cs.CY cs.LG

Penulis (3)

Ya'acov Ritov

Yuekai Sun

Ruofei Zhao

Format Sitasi

APA MLA BibTeX

Ritov, Y., Sun, Y., Zhao, R. (2017). On conditional parity as a notion of non-discrimination in machine learning. https://arxiv.org/abs/1706.08519

Akses Cepat

Lihat di Sumber

Informasi Jurnal

Tahun Terbit: 2017
Bahasa: en
Sumber Database: arXiv
Akses: Open Access ✓