Скачать с ютуб Dynamical, symplectic and stochastic perspectives on optimization – Michael Jordan – ICM2018 в хорошем качестве

Dynamical, symplectic and stochastic perspectives on optimization – Michael Jordan – ICM2018

Plenary Lecture 20 Dynamical, symplectic and stochastic perspectives on gradient-based optimization Michael Jordan Abstract: Our topic is the relationship between dynamical systems and optimization. This is a venerable, vast area in mathematics, counting among its many historical threads the study of gradient flow and the variational perspective on mechanics. We aim to build some new connections in this general area, studying aspects of gradient-based optimization from a continuous-time, variational point of view. We go beyond classical gradient flow to focus on second-order dynamics, aiming to show the relevance of such dynamics to optimization algorithms that not only converge, but converge quickly. ICM 2018 – International Congress of Mathematicians © www.icm2018.org     Os direitos sobre todo o material deste canal pertencem ao Instituto de Matemática Pura e Aplicada, sendo vedada a utilização total ou parcial do conteúdo sem autorização prévia e por escrito do referido titular, salvo nas hipóteses previstas na legislação vigente. The rights over all the material in this channel belong to the Instituto de Matemática Pura e Aplicada, and it is forbidden to use all or part of it without prior written authorization from the above mentioned holder, except in the cases prescribed in the current legislation.