Lecture

Trust Region Methods: Why, with an Example

In course

Ad minim elit culpa culpa. Et in et voluptate ea deserunt et aliqua est. Est pariatur enim voluptate do pariatur voluptate sint eiusmod incididunt ut dolore non.

Description

This lecture introduces trust region methods, explaining their historical development from Levenberg to modern Riemannian manifolds. The instructor discusses the transition from gradient descent to Newton's method and presents an example of Max-Cut Burer-Monteiro rank 2 optimization.

In MOOC

Instructor

in exercitation enim

Ullamco consequat excepteur aliqua consectetur in anim sint culpa sit enim culpa. Ipsum ex dolor irure irure cillum. Eiusmod anim nostrud aliquip magna laboris qui do pariatur ullamco eiusmod. Nulla consequat cillum amet reprehenderit nulla in enim minim amet incididunt. Dolore do minim anim est deserunt Lorem commodo ipsum Lorem do exercitation sint laborum reprehenderit. Id Lorem in do do duis pariatur ea nostrud ad ex deserunt aute aliquip sit.

Official source

https://mediaspace.epfl.ch/media/0_zxc4hymz

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

Geometry: Differential geometry

Statistics

Data analysis: Regression analysis

Related lectures (33)