Generalization in Deep Learning. Kawaguchi, K., Kaelbling, L. P., & Bengio, Y. In pages 112–148. December, 2022. arXiv:1710.05468 [cs, stat]
Generalization in Deep Learning [link]Paper  doi  abstract   bibtex   
This paper provides theoretical insights into why and how deep learning can generalize well, despite its large capacity, complexity, possible algorithmic instability, nonrobustness, and sharp minima, responding to an open question in the literature. We also discuss approaches to provide non-vacuous generalization guarantees for deep learning. Based on theoretical observations, we propose new open problems and discuss the limitations of our results.
@incollection{kawaguchi_generalization_2022,
	title = {Generalization in {Deep} {Learning}},
	url = {http://arxiv.org/abs/1710.05468},
	abstract = {This paper provides theoretical insights into why and how deep learning can generalize well, despite its large capacity, complexity, possible algorithmic instability, nonrobustness, and sharp minima, responding to an open question in the literature. We also discuss approaches to provide non-vacuous generalization guarantees for deep learning. Based on theoretical observations, we propose new open problems and discuss the limitations of our results.},
	urldate = {2023-01-06},
	author = {Kawaguchi, Kenji and Kaelbling, Leslie Pack and Bengio, Yoshua},
	month = dec,
	year = {2022},
	doi = {10.1017/9781009025096.003},
	note = {arXiv:1710.05468 [cs, stat]},
	keywords = {Computer Science - Artificial Intelligence, Computer Science - Machine Learning, Computer Science - Neural and Evolutionary Computing, Statistics - Machine Learning},
	pages = {112--148},
}

Downloads: 0