A Sharper Picture of Generalization in Transformers 事件

A Sharper Picture of Generalization in Transformers arXiv:2605.20988v2 Announce Type: replace-cross Abstract: We study transformers' generalization behavior on boolean domains from the perspective of the Fourier spectra of their target functions. In contrast to prior work (Edelman et al., 2022; Trauger & Tosh, 2024), which derived generalization bounds from Rademacher complexity, we investigate the feasibility of obtaining generalization bounds via PAC-Bayes theory. We show that sparse spectra