Lecture
Gradient Descent
In course
DEMO: voluptate laboris
Eu excepteur sunt nisi adipisicing nisi et eiusmod consequat adipisicing. Veniam nisi magna incididunt ut excepteur cillum veniam cillum deserunt adipisicing culpa magna nostrud ea. Nulla fugiat officia consectetur laboris commodo irure sint eiusmod sint est magna laboris consequat. Minim voluptate in commodo commodo adipisicing exercitation fugiat. Occaecat non eu commodo proident amet ex ut officia enim ullamco enim.
Description
This lecture covers optimization on manifolds, focusing on a family of gradient descent methods to minimize a smooth function on a manifold. The algorithm template for (Riemannian) gradient descent is discussed, emphasizing the aim to guarantee small gradients. The lecture also delves into Taylor expansions, first-order, and the concept of retraction and Riemannian metric on the manifold. The instructor explains the algorithm's steps and highlights the importance of ensuring small gradients for convergence. The lecture concludes with insights on global convergence and the regularity assumption, particularly the Lipschitz-type assumption. Various mathematical expressions and theorems are presented to support the concepts discussed.
In MOOC
Introduction to optimization on smooth manifolds: first order methods
Learn to optimize on smooth, nonlinear spaces: Join us to build your foundations (starting at "what is a manifold?") and confidently implement your first algorithm (Riemannian gradient descent).
Instructor
ullamco nisi
Nostrud qui dolore est irure nulla reprehenderit elit labore nostrud labore qui. Duis exercitation dolore incididunt incididunt aute ex nisi qui sunt. Lorem reprehenderit ullamco esse nulla sit voluptate. Voluptate amet consequat fugiat exercitation fugiat sunt sint. Ipsum ut laboris commodo nulla qui esse.
Official source
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
Related lectures (33)
Differential Forms on Manifolds
Introduces differential forms on manifolds, covering tangent bundles and intersection pairings.
Dynamics of Steady Euler Flows: New Results
Explores the dynamics of steady Euler flows on Riemannian manifolds, covering ideal fluids, Euler equations, Eulerisable flows, and obstructions to exhibiting plugs.
Differentiating vector fields: Why do it?MOOC: Introduction to optimization on smooth manifolds: first order methods
Explores the importance of differentiating vector fields and the correct methodology to achieve it, emphasizing the significance of going beyond the first order.
Topology of Riemann Surfaces
Covers the topology of Riemann surfaces, focusing on orientation and orientability.
Differential Forms Integration
Covers the integration of differential forms on smooth manifolds, including the concepts of closed and exact forms.