Normal Approximation for Stochastic Gradient Descent via Non-Asymptotic Rates of Martingale CLT

dc.contributor.author	Anastasiou, Andreas	en
dc.contributor.author	Balasubramanian, Krishnakumar	en
dc.contributor.author	Erdogdu, Murat A.	en
dc.coverage.spatial	USA	en
dc.creator	Anastasiou, Andreas	en
dc.creator	Balasubramanian, Krishnakumar	en
dc.creator	Erdogdu, Murat A.	en
dc.date.accessioned	2021-01-25T08:41:32Z
dc.date.available	2021-01-25T08:41:32Z
dc.date.issued	2019
dc.identifier.uri	http://gnosis.library.ucy.ac.cy/handle/7/62910
dc.description.abstract	We provide non-asymptotic convergence rates of the Polyak-Ruppert averaged stochastic gradient descent (SGD) to a normal random vector for a class of twice-differentiable test functions. A crucial ...	en
dc.language.iso	en	en
dc.publisher	Proceedings of Machine Learning Research (PMLR)	en
dc.source	Proceedings of the Thirty-Second Conference on Learning Theory	en
dc.source.uri	http://proceedings.mlr.press/v99/anastasiou19a.html
dc.title	Normal Approximation for Stochastic Gradient Descent via Non-Asymptotic Rates of Martingale CLT	en
dc.type	info:eu-repo/semantics/conferenceObject
dc.description.startingpage	115
dc.description.endingpage	137
dc.author.faculty	Σχολή Θετικών και Εφαρμοσμένων Επιστημών / Faculty of Pure and Applied Sciences
dc.author.department	Τμήμα Μαθηματικών και Στατιστικής / Department of Mathematics and Statistics
dc.type.uhtype	Conference Object	en

Files in this item

Files	Size	Format	View
There are no files associated with this item.