English

On the Mirage of Long-Range Dependency, with an Application to Integer Multiplication

Machine Learning 2026-04-07 v2 Artificial Intelligence

Abstract

Integer multiplication has long been considered a hard problem for neural networks, with the difficulty widely attributed to the O(n) long-range dependency induced by carry chains. We argue that this diagnosis is wrong: long-range dependency is not an intrinsic property of multiplication, but a mirage produced by the choice of computational spacetime. We formalize the notion of mirage and provide a constructive proof: when two n-bit binary integers are laid out as a 2D outer-product grid, every step of long multiplication collapses into a 3×33 \times 3 local neighborhood operation. Under this representation, a neural cellular automaton with only 321 learnable parameters achieves perfect length generalization up to 683×683\times the training range. Five alternative architectures -- including Transformer (6,625 params), Transformer+RoPE, and Mamba -- all fail under the same representation. We further analyze how partial successes locked the community into an incorrect diagnosis, and argue that any task diagnosed as requiring long-range dependency should first be examined for whether the dependency is intrinsic to the task or induced by the computational spacetime.

Keywords

Cite

@article{arxiv.2603.29069,
  title  = {On the Mirage of Long-Range Dependency, with an Application to Integer Multiplication},
  author = {Zichao Wei},
  journal= {arXiv preprint arXiv:2603.29069},
  year   = {2026}
}
R2 v1 2026-07-01T11:45:10.670Z