On the Minimal Degree Bias in Generalization on the Unseen for non-Boolean Functions

Denys Pushkin; Raphaël Berthier; Emmanuel Abbe

2024 ICML ICML 2024

On the Minimal Degree Bias in Generalization on the Unseen for non-Boolean Functions

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

Denys Pushkin, Raphaël Berthier, Emmanuel Abbe

Topics

Machine Learning > Optimization & Theory > Learning Theory Machine Learning > Optimization & Theory > Theory Deep Learning > Architectures > Transformers

Keywords

transformer random feature model generalization on the unseen (gotu) setting minimal degree interpolator q-ary data tokens sparse target regime

Download PDF