Fixed point compositionality via low-rank gluing rules in inhibition-dominated threshold-linear networks
Abstract
Brains routinely generate highly flexible and complex behaviors on a relatively stable structure and limited resources. A key mechanism underlying this ability is compositionality, which allows the brain to efficiently decompose complex tasks into simpler, reusable primitives. While network modularity has often been linked to compositionality in biological and artificial networks, a rigorous mathematical characterization of this relationship in nonlinear networks is still lacking. In this work, we formally investigate how structural modularity supports functional compositionality in inhibition-dominated threshold-linear networks (TLNs). We introduce a novel class of modular network assembly called low-rank gluings, where component subnetworks with arbitrary internal connectivity are connected via specific low-rank couplings. We prove that the global fixed points of these networks are constrained to be combinations of the local fixed points of their constituent modules. For a more structured subclass, called rank-1 gluings, we provide a complete characterization that determines which combinations of local fixed points yield global ones. We apply these results to graph-based networks, extending fixed point decomposition rules from combinatorial threshold-linear networks (CTLNs) to the more flexible family of generalized CTLNs (gCTLNs), thereby proving that these structural rules are more robust than initially posited. Finally, we demonstrate that these gluing rules provide a mathematically tractable recipe for engineering compositional dynamics, enabling the construction of networks with a combinatorially large repertoire of predictable attractors that can be understood from simpler component motifs, ranging from compositions of fixed points to compositional limit cycles.
Related
- Glider compositionality and information capacity in an E/I-balanced neuronal automaton
- Non-trivial compositionality in chimpanzees: an experimental demonstration
- Sequential chaotic oscillations in excitatory-inhibitory threshold-linear networks
- Brain-wide pathways for object identity and location are dominated by internal strategies
- Non‑monotonic reorganization of cortical neuron firing despite ongoing delta‑dominated activity
BibTeX
@misc{alvarez2026fixed,
title = {{Fixed point compositionality via low-rank gluing rules in inhibition-dominated threshold-linear networks}},
author = {Juliana Londono Alvarez},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2606.07336},
eprint = {2606.07336},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2606.07336},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - UNPB
TI - Fixed point compositionality via low-rank gluing rules in inhibition-dominated threshold-linear networks
AU - Juliana Londono Alvarez
PY - 2026
DA - 2026/09/28
PB - arXiv
DO - 10.48550/arxiv.2606.07336
UR - https://arxiv.org/abs/2606.07336
AB - Brains routinely generate highly flexible and complex behaviors on a relatively stable structure and limited resources. A key mechanism underlying this ability is compositionality, which allows the brain to efficiently decompose complex tasks into simpler, reusable primitives. While network modularity has often been linked to compositionality in biological and artificial networks, a rigorous mathematical characterization of this relationship in nonlinear networks is still lacking. In this work, we formally investigate how structural modularity supports functional compositionality in inhibition-dominated threshold-linear networks (TLNs). We introduce a novel class of modular network assembly called low-rank gluings, where component subnetworks with arbitrary internal connectivity are connected via specific low-rank couplings. We prove that the global fixed points of these networks are constrained to be combinations of the local fixed points of their constituent modules. For a more structured subclass, called rank-1 gluings, we provide a complete characterization that determines which combinations of local fixed points yield global ones. We apply these results to graph-based networks, extending fixed point decomposition rules from combinatorial threshold-linear networks (CTLNs) to the more flexible family of generalized CTLNs (gCTLNs), thereby proving that these structural rules are more robust than initially posited. Finally, we demonstrate that these gluing rules provide a mathematically tractable recipe for engineering compositional dynamics, enabling the construction of networks with a combinatorially large repertoire of predictable attractors that can be understood from simpler component motifs, ranging from compositions of fixed points to compositional limit cycles.
ER -