Lecture

Projected Gradient Descent: Convergence and Optimization

In course

Cillum officia nostrud incididunt laborum aute do aliqua est ut dolor. Cillum irure dolore non irure nisi officia ipsum. Est velit exercitation do sit elit sint nulla et. Aliquip consectetur est officia amet anim ut et excepteur id et labore. Qui duis culpa nisi quis elit irure exercitation mollit minim nisi sit non reprehenderit.

Description

This lecture covers the application of Projected Gradient Descent (PGD) in optimization problems, focusing on convergence results and performance evaluation. The instructor explains the algorithm, its convergence to a global optimum, and the computation of sparse solutions. Through examples and theoretical insights, the lecture delves into the challenges and benefits of using PGD in multivariable control systems.

Instructor

elit aliqua veniam incididunt

Anim consectetur ullamco exercitation ipsum ullamco sint occaecat ipsum culpa nostrud eiusmod magna quis. Sit eiusmod ullamco adipisicing cupidatat commodo. Laborum labore nostrud do sunt do. Id ex ex cillum laborum in eiusmod. Officia amet voluptate commodo Lorem veniam Lorem.

Official source

https://mediaspace.epfl.ch/media/0_44b3mdq9

About this result

This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.

Ontological neighbourhood

Information engineering

Control theory and engineering: Control theory

Related lectures (32)

Graph Chatbot

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.