9.520/6.860, Class 18

Class 18: Local Methods

Instructor: Sasha Rakhlin


We start by discussing the bias-variance trade-off, and then go on to discussing local methods: k-Nearest Neighbors and Nadaraya-Watson, before finishing with a discussion of interpolation.


Slides for this lecture: PDF

Class Reference Material

L. Rosasco, T. Poggio, Machine Learning: a Regularization Approach, MIT-9.520 Lectures Notes, Manuscript, Dec. 2017

Suggested Reading