Unified spectral analysis shows knowledge transfer efficacy arises from spectral horizon expansion in KD and spectral denoising in W2S, governed by implicit regularization and heterogeneous spectral learning speeds.
org/CorpusID:273185855
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
What Makes a Strong Model? A Unified Spectral Analysis of Knowledge Transfer over High-dimensional Linear Regression
Unified spectral analysis shows knowledge transfer efficacy arises from spectral horizon expansion in KD and spectral denoising in W2S, governed by implicit regularization and heterogeneous spectral learning speeds.