Lecture

Projected Gradient Descent and Quadratic Penalty

In course

Mollit sunt commodo minim aliqua aute elit reprehenderit ex ipsum aute minim minim. Ullamco nostrud id non aliquip. Culpa aliquip et enim officia fugiat ad eu. Culpa nisi eiusmod aliqua nostrud consequat reprehenderit labore dolor anim consectetur sit.

Description

This lecture covers Projected Gradient Descent (PGD) and Quadratic Penalty methods, focusing on the assumptions and convergence properties. It explains how PGD works under different conditions and how Quadratic Penalty methods can be used to solve optimization problems. The lecture also discusses the convergence of PGD and the optimality conditions for Quadratic Penalty methods.

Instructor

cupidatat occaecat

Do qui dolore et sit cillum ex in laborum. Esse enim nisi velit reprehenderit eu nulla elit. Commodo esse officia reprehenderit velit.

Official source

https://mediaspace.epfl.ch/media/0_vms2fqv6

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

Mathematics

Topology: General topology

Theoretical computer science

Algorithms and data structures: Combinatorial optimization

Related lectures (39)

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.