Sparse low-degree Fourier spectra allow flat minima in transformers for boolean functions up to context-length sparsity, enabling non-vacuous PAC-Bayes generalization bounds via an idealized low-sharpness learner.
remainder perturbations
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
-
A Sharper Picture of Generalization in Transformers
Sparse low-degree Fourier spectra allow flat minima in transformers for boolean functions up to context-length sparsity, enabling non-vacuous PAC-Bayes generalization bounds via an idealized low-sharpness learner.