Lecture

Gradient Descent for Linear MSE

In course
DEMO: nostrud exercitation aliqua ut
Mollit sunt est veniam dolore nulla labore. Ea aute sit incididunt adipisicing sint eu nulla Lorem officia ullamco consequat. Consectetur sunt officia nisi sunt non veniam elit sunt.
Login to see this section
Description

This lecture covers the concept of Gradient Descent for Linear Mean Squared Error (MSE) in machine learning. It explains the computation of the gradient, the complexity of computing the gradient, and the variant with an offset term. The lecture also delves into Stochastic Gradient Descent, the use of penalty functions for constrained optimization, and the implementation issues such as adaptive step-size selection and feature normalization. Additionally, it discusses non-convex optimization, stopping criteria, optimality conditions, and the transformation of constrained problems into unconstrained ones.

This video is available exclusively on Mediaspace for a restricted audience. Please log in to MediaSpace to access it if you have the necessary permissions.

Watch on Mediaspace
Instructors (2)
do est pariatur
Id id aute id aliquip aute anim officia culpa nulla duis voluptate. Deserunt eu ut eiusmod et anim eiusmod quis aliqua mollit ex nisi. Ipsum occaecat qui quis minim do nostrud reprehenderit aliqua velit pariatur.
excepteur mollit
Lorem velit officia occaecat laboris non mollit. Nostrud et sint laborum dolore officia deserunt officia occaecat Lorem anim id ex. Dolor quis commodo Lorem incididunt minim enim eiusmod irure nulla est officia labore. Pariatur officia sit laborum magna non elit consectetur laborum irure esse excepteur elit. Est reprehenderit officia culpa exercitation sint officia consectetur nisi minim laboris officia.
Login to see this section
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.