Lecture

Nonconvex Optimization: Challenges and Strategies

In course

Amet do non incididunt nulla labore occaecat velit anim excepteur in cupidatat aliqua. Ipsum irure in aliqua non cillum sunt adipisicing quis ullamco fugiat non. Sunt non duis consequat eiusmod consectetur enim. Adipisicing labore amet voluptate irure sunt do cillum nulla ea.

Description

This lecture delves into nonconvex optimization problems with nonlinear constraints, focusing on blind image deconvolution as an illustrative example. It covers standard convex optimization formulations, SDP relaxations, and applications in graph theory, clustering, and neural networks. The instructor discusses the challenges in convergence guarantees and introduces strategies like the Homotopy Conditional Gradient Method and Augmented Lagrangian approach.

Instructor

id qui Lorem eu

Commodo ex reprehenderit elit labore. Sint laboris exercitation sunt ea incididunt velit deserunt non. Est amet ipsum ut culpa velit ipsum et ut irure consectetur voluptate dolor. Ipsum dolore pariatur ipsum elit. In excepteur fugiat proident officia nostrud Lorem. Duis nulla consequat ex ullamco eu ad.

Official source

https://mediaspace.epfl.ch/media/0_nvjhf1ru

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

Discrete mathematics: Graph theory

Information engineering

Machine learning: Unsupervised learning

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.