Benjamin Fehrman (University of Oxford)
Thursday, May 14, 2020 - 17:00
MPI für Mathematik in den Naturwissenschaften Leipzig
 ,    , Videobroadcast, 3. Etage
We prove the local convergence to minima and estimates on the rate of convergence for the stochastic gradient descent method in the case of not necessarily globally convex nor contracting objective functions. In particular, the results are applicable to simple objective functions arising in machine learning. https://arxiv.org/abs/1904.01517

One day before the seminar, an announcement with the Zoom link will be sent to those who registered with Valeria Hünniger. For this please contact her at Valeria Hünniger.

submitted by Valeria Hünniger (Valeria.Huenniger@mis.mpg.de, 0341 9959 50)