Lecture
Understanding Generalization: Implicit Bias & Optimization
Description
This lecture delves into the trade-off between complexity and risk in machine learning models, showcasing how test error decreases with increasing model complexity. It explores the benefits of overparametrization, the implicit bias of optimization algorithms, and the concept of implicit regularization. The discussion extends to the stability of optimization algorithms, the double descent phenomenon, and the probability of interpolation in high-dimensional datasets.
Official source
About this result
This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.