Explore the intriguing phenomenon of the double descent effect in modern machine learning through this comprehensive lecture by Yizhe Zhu from the University of Southern California. Delve into the transition from simplicity to complexity in machine learning models, gaining insights into how this effect impacts model performance and generalization. Discover the implications of this phenomenon for designing and optimizing machine learning algorithms, and understand its relevance in various applications across the field.
From Simplicity to Complexity: The Double Descent Effect in Modern Machine Learning
Banach Center via YouTube
Overview
Syllabus
From simplicity to complexity: the double descent effect in modern machine learning
Taught by
Banach Center
Related Courses
-
The Elusive Generalization: Classical Bounds to Double Descent to Grokking
-
From Classical Statistics to Modern ML - The Lessons of Deep Learning - Mikhail Belkin
-
Grokking - Generalization Beyond Overfitting on Small Algorithmic Datasets
-
From Classical Statistics to Modern Machine Learning
-
Modern Paradigms of Generalization - The Heliocentric Model of Aristarchus
-
Overfitting: Benign, Tempered and Harmful - Lecture on Machine Learning Regularization
