Explore advanced concepts in statistical learning with Robert Schapire from Microsoft Research in this hour-long lecture. Delve into topics such as expected value theorems, ghost sample bounds, and PAC learning. Gain insights into finite hypothesis spaces and the role of randomness in statistical learning. Enhance your understanding of statistical learning theory through detailed proofs and comprehensive explanations provided by an expert in the field.
Overview
Syllabus
Intro
Expected Value
Theorem
Proof
Ghost Sample
Bounds
Randomness
Summary
Finite Hypothesis Space
Conclusion
PAC Learning
Taught by
Paul G. Allen School
Related Courses
-
Studying Generalization in Deep Learning via PAC-Bayes
-
Statistical Learning Theory for Modern Machine Learning - John Shawe-Taylor
-
Statistical Learning - Robert Schapire, Microsoft Research
-
Learning Automata with Hankel Matrices - Borja Balle, Amazon Research Cambridge
-
Statistical Theory
-
Multivariate Statistical Analysis
