Normal Approximation for Stochastic Gradient Descent via Non-Asymptotic Rates of Martingale CLT
Ημερομηνία
2019Συγγραφέας
Anastasiou, AndreasBalasubramanian, Krishnakumar
Erdogdu, Murat A.
Εκδότης
Proceedings of Machine Learning Research (PMLR)Place of publication
USASource
Proceedings of the Thirty-Second Conference on Learning TheoryPages
115-137Google Scholar check
Metadata
Εμφάνιση πλήρους εγγραφήςΕπιτομή
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 ...