Tutorial: A generalization error estimation for overparameterized models via WAIC
##article.authors##
-
Akifumi Okuno
Institute of Statistical Mathematics, School of Statistical Thinking
https://researchmap.jp/aokuno
-
Keisuke Yano
Institute of Statistical Mathematics, Department of Statistical Inference and Mathematics
https://researchmap.jp/keisukeyano
DOI:
https://doi.org/10.51094/jxiv.537Keywords:
WAIC, Neural Network, Overparameterized Model, Singular Model, Degree of Freedom, GeneralizationAbstract
本稿は Journal of Computational and Graphical Statistics 誌に採択された我々の原著論文:
Okuno, A. and Yano, K. (2023). A generalization gap estimation for overparameterized models via the Langevin functional variance. Journal of Computational and Graphical Statistics. https://doi.org/10.1080/10618600.2023.2197488.
に関する解説です．
Conflicts of Interest Disclosure
No conflict of interest.Downloads *Displays the aggregated results up to the previous day.
References
Okuno, A. and Yano, K. (2023). A generalization gap estimation for overparameterized models via the Langevin functional variance. Journal of Computational and Graphical Statistics. https://doi.org/10.1080/10618600.2023.2197488.
Watanabe, S. (2010). Asymptotic equivalence of bayes cross validation and widely applicable information criterion in singular learning theory. Journal of Machine Learning Research, 11(116):3571–3594.
Downloads
Posted
Submitted: 2023-10-24 06:17:20 UTC
Published: 2023-10-25 23:29:53 UTC
License
Copyright (c) 2023
Akifumi Okuno
Keisuke Yano
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
