pith. sign in

Are transformers with one layer self-attention using low-rank weight matrices universal approximators?arXiv preprint arXiv:2307.14023

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.LG 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

Transformer Approximations from ReLUs

cs.LG · 2026-04-27 · unverdicted · novelty 7.0

A recipe translates ReLU approximations to softmax attention with target-specific economic bounds for multiplication, reciprocal computation, and min/max primitives.

citing papers explorer

Showing 1 of 1 citing paper.

  • Transformer Approximations from ReLUs cs.LG · 2026-04-27 · unverdicted · none · ref 3

    A recipe translates ReLU approximations to softmax attention with target-specific economic bounds for multiplication, reciprocal computation, and min/max primitives.