Composing Linear Layers from Irreducibles

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Pence, Travis, Yamada, Daisuke, Singh, Vikas
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866918334963908608
author Pence, Travis
Yamada, Daisuke
Singh, Vikas
author_facet Pence, Travis
Yamada, Daisuke
Singh, Vikas
contents Contemporary large models often exhibit behaviors suggesting the presence of low-level primitives that compose into modules with richer functionality, but these fundamental building blocks remain poorly understood. We investigate this compositional structure in linear layers by asking: can we identify/synthesize linear transformations from a minimal set of geometric primitives? Using Clifford algebra, we show that linear layers can be expressed as compositions of bivectors -- geometric objects encoding oriented planes -- and introduce a differentiable algorithm that decomposes them into products of rotors. This construction uses only O(log^2 d) parameters, versus O(d^2) required by dense matrices. Applied to the key, query, and value projections in LLM attention layers, our rotor-based layers match the performance of strong baselines such as block-Hadamard and low-rank approximations. Our findings provide an algebraic perspective on how these geometric primitives can compose into higher-level functions within deep models.
format Preprint
id arxiv_https___arxiv_org_abs_2507_11688
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Composing Linear Layers from Irreducibles
Pence, Travis
Yamada, Daisuke
Singh, Vikas
Machine Learning
I.2.6
Contemporary large models often exhibit behaviors suggesting the presence of low-level primitives that compose into modules with richer functionality, but these fundamental building blocks remain poorly understood. We investigate this compositional structure in linear layers by asking: can we identify/synthesize linear transformations from a minimal set of geometric primitives? Using Clifford algebra, we show that linear layers can be expressed as compositions of bivectors -- geometric objects encoding oriented planes -- and introduce a differentiable algorithm that decomposes them into products of rotors. This construction uses only O(log^2 d) parameters, versus O(d^2) required by dense matrices. Applied to the key, query, and value projections in LLM attention layers, our rotor-based layers match the performance of strong baselines such as block-Hadamard and low-rank approximations. Our findings provide an algebraic perspective on how these geometric primitives can compose into higher-level functions within deep models.
title Composing Linear Layers from Irreducibles
topic Machine Learning
I.2.6
url https://arxiv.org/abs/2507.11688