/Advanced-Theoretical-Machine-Learning

Based on the book: "Understanding Machine Learning: From Theory to Algorithms"

Advanced Theoretical Machine Learning

Based on the book: "Understanding Machine Learning: From Theory to Algorithms" by Shai Shalev-Shwartz and Shai Ben-David

Course taught during the Artificial Intelligence master's program, 1st Year, 2nd Semester, 2021

University of Bucharest, Faculty of Mathematics and Computer Science

Professor: Bogdan Alexe

Laboratory: Bogdan Alexe

Exam: 50% * Assignment 1 + 50% * Assignment 2

Contents

  • Empirical Risk Minimization
  • Probably Approximately Correct learning
  • Learning finite classes
  • PAC learnability of a class H
  • Agnostic PAC learning
  • Uniform Convergence
  • The No-Free-Lunch theorem
  • The Bias-Complexity tradeoff
  • Shattering and VC-dimension
  • The fundamental theorem of statistical learning
  • Lemma (Sauer – Shelah – Perles)
  • AdaBoost Algorithm

Examples

AdaBoost VC dimension and hypothesis finding algorithm for all strings of size M subspace