Lower error bounds for the stochastic gradient descent optimization algorithm: Sharp convergence rates for slowly and fast decaying learning rates
Metadata only
Date
2020-04Type
- Journal Article
Citations
Cited null times in
Web of Science
Cited 1 times in
Scopus
ETH Bibliography
yes
Altmetrics
Publication status
publishedExternal links
Journal / series
Journal of ComplexityVolume
Pages / Article No.
Publisher
ElsevierSubject
SGD; Lower bounds; Machine learning; Error analysisOrganisational unit
03951 - Jentzen, Arnulf (ehemalig) / Jentzen, Arnulf (former)
02501 - Seminar für Angewandte Mathematik / Seminar for Applied Mathematics
02204 - RiskLab / RiskLab
Funding
175699 - Higher order numerical approximation methods for stochastic partial differential equations (SNF)
Related publications and datasets
Is new version of: https://doi.org/10.3929/ethz-b-000347647
More
Show all metadata
Citations
Cited null times in
Web of Science
Cited 1 times in
Scopus
ETH Bibliography
yes
Altmetrics