How Spurious Features are Memorized: Precise Analysis for Random and NTK Features

Simone Bombari; Marco Mondelli

2024 ICML ICML 2024

How Spurious Features are Memorized: Precise Analysis for Random and NTK Features

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

Authors

Simone Bombari, Marco Mondelli

Topics

Machine Learning > Optimization & Theory > Learning Theory Machine Learning > Optimization & Theory > Theory

Keywords

feature alignment neural tangent kernel stability random feature spurious feature memorization

Download PDF