Fairness Without Demographics in Repeated Loss Minimization

Fairness Without Demographics in Repeated Loss Minimization. Hashimoto, T., Srivastava, M., Namkoong, H., & Liang, P. In International Conference on Machine Learning, pages 1929–1938.

Paper abstract bibtex

Machine learning models (e.g., speech recognizers) trained on average loss suffer from representation disparity—minority groups (e.g., non-native speakers) carry less weight in the training objecti...

@inproceedings{hashimoto_fairness_2018,
	title = {Fairness Without Demographics in Repeated Loss Minimization},
	url = {http://proceedings.mlr.press/v80/hashimoto18a.html},
	abstract = {Machine learning models (e.g., speech recognizers) trained on average loss suffer from representation disparity—minority groups (e.g., non-native speakers) carry less weight in the training objecti...},
	eventtitle = {International Conference on Machine Learning},
	pages = {1929--1938},
	booktitle = {International Conference on Machine Learning},
	author = {Hashimoto, Tatsunori and Srivastava, Megha and Namkoong, Hongseok and Liang, Percy},
	urldate = {2019-07-12},
	date = {2018-07-03},
	langid = {english}
}

Downloads: 0