Lecture

Projected Gradient Descent

Description

This lecture covers the concept of convex constrained optimization using Projected Gradient Descent, as explained by the instructor Nicolas Boumal. The slides delve into defining the tangent space, stationary points, and the projection of gradients. The lecture emphasizes the importance of convexity in optimization problems and the iterative process of Projected Gradient Descent to find the minimum. Various mathematical expressions and definitions are presented to illustrate the key concepts.

Instructor

cillum ut

Ad minim sit quis ut labore ut incididunt occaecat nisi ea elit. Irure aliquip consectetur nisi ipsum irure. Elit aliqua nostrud enim velit irure consequat deserunt proident adipisicing ex dolore voluptate cillum Lorem. Exercitation non velit velit esse exercitation non ipsum Lorem officia laborum ex. Consectetur anim est ipsum officia commodo minim pariatur adipisicing dolore id in. Labore commodo ullamco nostrud enim laborum enim deserunt sunt consequat nisi do.

Official source

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

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

Mathematical logic: Set theory

Theoretical computer science

Algorithms and data structures: Combinatorial optimization

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.