Lecture

Optimization for Machine Learning: Newton's and Quasi-Newton Methods

Description

This lecture covers Optimization for Machine Learning, focusing on Newton's and Quasi-Newton Methods. It explains the 1-dimensional case of Newton-Raphson method, the Babylonian method for computing square roots, and the secant method. The lecture delves into the convergence of Newton's method, the secant condition, and Quasi-Newton methods. It discusses the downsides of Newton's method, the secant condition, and the development of Quasi-Newton methods. The lecture also touches on strong convexity, bounded inverse Hessians, and the super-exponential convergence of Newton's method. Additionally, it explores the affine invariance of Newton's method and the convergence in one step on quadratic functions.

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
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.