Skip to content
conftrace_
2024 ICML ICML 2024

Revisit the Essence of Distilling Knowledge through Calibration

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

Wen-shu Fan, Su Lu, Xin-Chun Li, De-Chuan Zhan, Le Gan

Topics

Artificial Intelligence > Core AI > Model Compression Machine Learning > Optimization & Theory > Learning Theory Deep Learning > Learning Types > Transfer Learning

Keywords

calibration knowledge distillation kl divergence ranking-based loss capacity mismatch large model
Download PDF