English

Average-Hard Attention Transformers are Constant-Depth Uniform Threshold Circuits

Computation and Language 2023-08-23 v2 Computational Complexity Machine Learning

Abstract

Transformers have emerged as a widely used neural network model for various natural language processing tasks. Previous research explored their relationship with constant-depth threshold circuits, making two assumptions: average-hard attention and logarithmic precision for internal computations relative to input length. Merrill et al. (2022) prove that average-hard attention transformers recognize languages that fall within the complexity class TC0, denoting the set of languages that can be recognized by constant-depth polynomial-size threshold circuits. Likewise, Merrill and Sabharwal (2023) show that log-precision transformers recognize languages within the class of uniform TC0. This shows that both transformer models can be simulated by constant-depth threshold circuits, with the latter being more robust due to generating a uniform circuit family. Our paper shows that the first result can be extended to yield uniform circuits as well.

Keywords

Cite

@article{arxiv.2308.03212,
  title  = {Average-Hard Attention Transformers are Constant-Depth Uniform Threshold Circuits},
  author = {Lena Strobl},
  journal= {arXiv preprint arXiv:2308.03212},
  year   = {2023}
}
R2 v1 2026-06-28T11:49:20.319Z