Stable non-minimal fixed points of threshold-linear networks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Geneson, Jesse
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918191700115456
author Geneson, Jesse
author_facet Geneson, Jesse
contents In threshold-linear networks (TLNs), a fixed point is called minimal if no proper subset of its support is also a fixed point. Curto et al (Advances in Applied Mathematics, 2024) conjectured that every stable fixed point of any TLN must be a minimal fixed point. We provide a counterexample to this conjecture: an explicit competitive TLN on 3 neurons that exhibits a stable fixed point whose support is not minimal (it contains the support of another stable fixed point). We prove that there is no competitive TLN on 2 neurons which contains a stable non-minimal fixed point, so our 3-neuron construction is the smallest such example. By expanding our base example, we show for any positive integers $i, j$ with $i < j-1$ that there exists a competitive TLN with stable fixed point supports $τ\subsetneq σ$ for which $|τ| = i$ and $|σ| = j$. Using a different expansion of our base example, we also show that chains of nested stable fixed points in competitive TLNs can be made arbitrarily long.
format Preprint
id arxiv_https___arxiv_org_abs_2511_05517
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Stable non-minimal fixed points of threshold-linear networks
Geneson, Jesse
Neurons and Cognition
Discrete Mathematics
Combinatorics
In threshold-linear networks (TLNs), a fixed point is called minimal if no proper subset of its support is also a fixed point. Curto et al (Advances in Applied Mathematics, 2024) conjectured that every stable fixed point of any TLN must be a minimal fixed point. We provide a counterexample to this conjecture: an explicit competitive TLN on 3 neurons that exhibits a stable fixed point whose support is not minimal (it contains the support of another stable fixed point). We prove that there is no competitive TLN on 2 neurons which contains a stable non-minimal fixed point, so our 3-neuron construction is the smallest such example. By expanding our base example, we show for any positive integers $i, j$ with $i < j-1$ that there exists a competitive TLN with stable fixed point supports $τ\subsetneq σ$ for which $|τ| = i$ and $|σ| = j$. Using a different expansion of our base example, we also show that chains of nested stable fixed points in competitive TLNs can be made arbitrarily long.
title Stable non-minimal fixed points of threshold-linear networks
topic Neurons and Cognition
Discrete Mathematics
Combinatorics
url https://arxiv.org/abs/2511.05517