arXiv stat.ML
· Papers
Standard Transformers Achieve the Minimax Rate in Nonparametric Regression with $C^{s,lambda}$ Targets
arXiv:2602.20555v2 Announce Type: replace Abstract: The tremendous success of Transformer models in fields such as large language models and computer vision necessitates a rigorous theoretical investigation. To the best of our knowledge, this paper is the first work proving that standard Transformers can approximate H