[IDA ML Seminar] IDA Machine Learning Seminar on Wednesday, May 19, 15:15

[Fredrik Lindsten]

Welcome to the IDA Machine Learning Seminar on Wednesday, May 19, 15:15

Yura Malitsky, Linköping University

Adaptive gradient descent without descent
Abstract: In this talk I will present some recent results for the most classical optimization method - gradient descent. We will show that a simple zero cost rule is sufficient to completely automate gradient descent. The method adapts to the local geometry, with convergence guarantees depending only on the smoothness in a neighborhood of a solution. The presentation is based on a joint work with K. Mishchenko, see https://arxiv.org/abs/1910.09529

Zoom link: https://liu-se.zoom.us/j/69011766298

-------
The list of future seminars in the series is available at http://www.ida.liu.se/research/machinelearning/seminars/.
Welcome!​
IDA Machine Learning Group
Linköping University

-------------- next part --------------
En HTML-bilaga skiljdes ut...
URL: <http://lists.liu.se/pipermail/ml-seminars/attachments/20210512/aedf1ba3/attachment.html>