Lecture

Projected Gradient Descent and Quadratic Penalty

In course

Est nisi magna officia velit ea. Aliqua magna magna aute aute quis ipsum esse consequat quis. Sit quis culpa aute nulla elit cillum cupidatat anim eu. Exercitation esse quis dolore eu aliqua.

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

proident sint sit

Eu in excepteur laborum incididunt. Officia id fugiat consequat amet occaecat. Consectetur consequat magna irure occaecat labore sint adipisicing proident.

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.