Skip to content
conftrace_
2025 ICML ICML 2025

Discrepancies are Virtue: Weak-to-Strong Generalization through Lens of Intrinsic Dimension

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

Yijun Dong, Yicheng Li, Yunai Li, Jason D. Lee, Qi Lei

Topics

Machine Learning > Core Methods > Regression Machine Learning > Optimization & Theory > Learning Theory Deep Learning > Learning Types > Transfer Learning

Keywords

sample complexity intrinsic dimension variance reduction ridgeless regression performance gap pseudo-labels
Download PDF