来源：https://mostafa-samir.github.io/
作者：Mostafa Samir

Machine Learning Theory – Part 1: Introduction

1. Motivation
2. Who is this Series for?
3. Prerequisites
4. Cautions
5. Formalizing the Learning Problem
   • The Target Function
   • The Hypothesis
   • The Loss Function
   • The Generalization Error
   • Is the Learning Problem Solvable?
6. References and Additional Readings
   • Share
   • Comments

Machine Learning Theory – Part 2: Generalization Bounds

1. Independently, and Identically Distributed
2. The Law of Large Numbers
3. Hoeffding’s inequality
4. Generalization Bound: 1st Attempt
5. Examining the Independence Assumption
6. The Symmetrization Lemma
7. The Growth Function
8. The VC-Dimension
9. The VC Generalization Bound
10. Distribution-Based Bounds
11. One Inequality to Rule Them All
12. References and Additional Readings
    • Share
    • Comments

Machine Learning Theory – Part 3: Regularization and the Bias-variance Trade-off

1. Why rich hypotheses are bad?
2. The Bias-variance Decomposition
   • A Little Exercise
3. Taming the Rich
4. References and Additional Readings
   • Share
   • Comments