A learnable two-sided Laplace transform attention layer is claimed to be linear-time and competitive, but the described computation of softmax over the full relevance matrix remains quadratic.
Findings of the 2014 workshop on statistical ma- chine translation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
REJECT 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Adaptive Two Sided Laplace Transforms: A Learnable, Interpretable, and Scalable Replacement for Self-Attention
A learnable two-sided Laplace transform attention layer is claimed to be linear-time and competitive, but the described computation of softmax over the full relevance matrix remains quadratic.