Tutorial: Outlier-Robust Neural Network Training
##article.authors##
-
Akifumi Okuno
Institute of Statistical Mathematics, Department of Fundamental Statistical Mathematics
https://researchmap.jp/aokuno
-
Shotaro Yagishita
Institute of Statistical Mathematics, Risk Analysis Research Center
https://researchmap.jp/Shotaro_Yagishita
DOI:
https://doi.org/10.51094/jxiv.928Keywords:
Neural Network, Robust Estimation, Trimmed Loss, Higher-Order Variation RegularizationAbstract
本稿は外れ値にロバストなニューラルネットの学習に関する我々のプレプリント Okuno and Yagishita (2024) に関する解説です．解説の平易さを優先するため，厳密な記述については当該プレプリントをご参照ください．
Conflicts of Interest Disclosure
No conflict of interest.Downloads *Displays the aggregated results up to the previous day.
References
Okuno, A. and Yagishita, S. (2024). Outlier-robust neural network training: Efficient optimization of transformed trimmed loss with variation regularization. arXiv preprint arXiv:2308.02293.
Robbins, H. and Monro, S. (1951). A Stochastic Approximation Method. The Annals of Mathematical Statistics, 22(3):400–407.
Yagishita, S. (2024). Fast algorithm for sparse least trimmed squares via trimmed-regularized reformulation. arXiv preprint arXiv:2410.04554.
Downloads
Posted
Submitted: 2024-10-10 10:46:07 UTC
Published: 2024-10-18 00:31:56 UTC
License
Copyright (c) 2024
Akifumi Okuno
Shotaro Yagishita
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
