Class 13: The Learning Problem and Regularization

Instructor: Sasha Rakhlin

Description

We reintroduce the setting of statistical learning and then go on to discuss the no-free lunch theorem and the perceptron algorithm.

Slides

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

Chapter 2 - Foundational Results

Note: The course notes, in the form of the circulated book draft is the reference material for this class. Related and older material can be accessed through previous year offerings of the course.

Further Reading

• L. Devroye, L. Gyorfi, G. Lugosi, A Probabilistic Theory of Pattern Recognition, Springer, 1996.
• O. Bousquet, S. Boucheron, G. Lugosi Introduction to Statistical Learning Theory, Advanced Lectures on Machine Learning pp 169-207.