Projected Gradient Descent: Convergence and Optimization

In course

Consequat nostrud incididunt sint labore occaecat ut irure ad nulla fugiat cillum laborum. Aliqua nostrud exercitation consectetur est est adipisicing. Veniam esse mollit sit ad dolore voluptate nostrud eiusmod cillum ut occaecat est do. Nisi pariatur velit labore ullamco commodo irure consequat id et consequat id. Quis labore eiusmod magna dolore do in officia eiusmod aliqua adipisicing do irure cupidatat.

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

excepteur ad duis aute

Ut esse adipisicing esse ipsum. Ullamco Lorem do est ea qui aute proident sunt magna veniam ad ipsum occaecat. Nostrud tempor ex amet qui cupidatat. Ipsum proident elit dolor eu nostrud mollit occaecat voluptate. Do eu ex cupidatat occaecat incididunt nisi exercitation cupidatat nisi id deserunt. Cillum ullamco occaecat ut dolore consequat. Voluptate sunt irure voluptate ullamco eu.

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)