On Symmetric Losses for Learning from Corrupted Labels

Autor:	Charoenphakdee, N., Lee, J., Masashi Sugiyama
Rok vydání:	2019
Předmět:	FOS: Computer and information sciences Computer Science - Machine Learning Statistics - Machine Learning Machine Learning (stat.ML) Machine Learning (cs.LG)
Zdroj:	Scopus-Elsevier
DOI:	10.48550/arxiv.1901.09314
Popis:	This paper aims to provide a better understanding of a symmetric loss. First, we emphasize that using a symmetric loss is advantageous in the balanced error rate (BER) minimization and area under the receiver operating characteristic curve (AUC) maximization from corrupted labels. Second, we prove general theoretical properties of symmetric losses, including a classification-calibration condition, excess risk bound, conditional risk minimizer, and AUC-consistency condition. Third, since all nonnegative symmetric losses are non-convex, we propose a convex barrier hinge loss that benefits significantly from the symmetric condition, although it is not symmetric everywhere. Finally, we conduct experiments to validate the relevance of the symmetric condition. Comment: ICML2019 with minor typo fixes
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_dedup___::228f19a3a21d83be0e8bc8fde2cbf113 Zobrazit plný text záznamu