English

Transformers are Universal Predictors

Machine Learning 2023-07-18 v1 Computation and Language

Abstract

We find limits to the Transformer architecture for language modeling and show it has a universal prediction property in an information-theoretic sense. We further analyze performance in non-asymptotic data regimes to understand the role of various components of the Transformer architecture, especially in the context of data-efficient training. We validate our theoretical analysis with experiments on both synthetic and real datasets.

Keywords

Cite

@article{arxiv.2307.07843,
  title  = {Transformers are Universal Predictors},
  author = {Sourya Basu and Moulik Choraria and Lav R. Varshney},
  journal= {arXiv preprint arXiv:2307.07843},
  year   = {2023}
}

Comments

Neural Compression Workshop (ICML 2023)

R2 v1 2026-06-28T11:31:22.169Z