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 arxiv.org/abs/1910.09529.

optimization and control

Audience: researchers in the topic

Variational Analysis and Optimisation Webinar

Series comments: Register on www.mocao.org/va-webinar/ to receive information about the zoom connection.