The perils of being unhinged: On the accuracy of classifiers minimizing a noise-robust convex loss

8 December 2021

Papers citing "The perils of being unhinged: On the accuracy of classifiers minimizing a noise-robust convex loss"

9 / 9 papers shown

Title
On Symmetric Losses for Learning from Corrupted Labels Nontawat Charoenphakdee Jongyeong Lee Masashi Sugiyama NoLa 51 105 0 27 Jan 2019
Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels Zhilu Zhang M. Sabuncu NoLa 74 2,595 0 20 May 2018
Robust Loss Functions under Label Noise for Deep Neural Networks Aritra Ghosh Himanshu Kumar P. Sastry NoLa OOD 61 955 0 27 Dec 2017
The Implicit Bias of Gradient Descent on Separable Data Daniel Soudry Elad Hoffer Mor Shpigel Nacson Suriya Gunasekar Nathan Srebro 121 913 0 27 Oct 2017
Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach Giorgio Patrini A. Rozza A. Menon Richard Nock Zhuang Li NoLa 90 1,448 0 13 Sep 2016
Learning with Symmetric Label Noise: The Importance of Being Unhinged Brendan van Rooyen A. Menon Robert C. Williamson NoLa 133 311 0 28 May 2015
Making Risk Minimization Tolerant to Label Noise Aritra Ghosh Naresh Manwani P. Sastry NoLa 116 214 0 14 Mar 2014
Margins, Shrinkage, and Boosting Matus Telgarsky 57 73 0 18 Mar 2013
Noise Tolerance under Risk Minimization Naresh Manwani S. M. I. P. S. Sastry NoLa 150 276 0 24 Sep 2011