Synchronization on circles and spheres with nonlinear interactions

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Criscitiello, Christopher, Rebjock, Quentin, McRae, Andrew D., Boumal, Nicolas
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912850105073664
author Criscitiello, Christopher
Rebjock, Quentin
McRae, Andrew D.
Boumal, Nicolas
author_facet Criscitiello, Christopher
Rebjock, Quentin
McRae, Andrew D.
Boumal, Nicolas
contents We consider the dynamics of $n$ points on a sphere in $\mathbb{R}^d$ ($d \geq 2$) which attract each other according to a function $φ$ of their inner products. When $φ$ is linear ($φ(t) = t$), the points converge to a common value (i.e., synchronize) in various connectivity scenarios: this is part of classical work on Kuramoto oscillator networks. When $φ$ is exponential ($φ(t) = e^{βt}$), these dynamics correspond to a limit of how idealized transformers process data, as described by Geshkovski et al. (2025). Accordingly, they ask whether synchronization occurs for exponential $φ$. The answer depends on the dimension $d$. In the context of consensus for multi-agent control, Markdahl et al. (2018) show that for $d \geq 3$ (spheres), if the interaction graph is connected and $φ$ is increasing and convex, then the system synchronizes. We give a separate proof of this result. What is the situation on circles ($d=2$)? First, we show that $φ$ being increasing and convex is no longer sufficient (even for complete graphs). Then we identify a new condition under which we do have synchronization on the circle (namely, if the Taylor coefficients of $φ'$ are decreasing). As a corollary, this provide synchronization for exponential $φ$ with $β\in (0, 1]$. The proofs are based on nonconvex landscape analysis.
format Preprint
id arxiv_https___arxiv_org_abs_2405_18273
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Synchronization on circles and spheres with nonlinear interactions
Criscitiello, Christopher
Rebjock, Quentin
McRae, Andrew D.
Boumal, Nicolas
Optimization and Control
Machine Learning
Dynamical Systems
We consider the dynamics of $n$ points on a sphere in $\mathbb{R}^d$ ($d \geq 2$) which attract each other according to a function $φ$ of their inner products. When $φ$ is linear ($φ(t) = t$), the points converge to a common value (i.e., synchronize) in various connectivity scenarios: this is part of classical work on Kuramoto oscillator networks. When $φ$ is exponential ($φ(t) = e^{βt}$), these dynamics correspond to a limit of how idealized transformers process data, as described by Geshkovski et al. (2025). Accordingly, they ask whether synchronization occurs for exponential $φ$. The answer depends on the dimension $d$. In the context of consensus for multi-agent control, Markdahl et al. (2018) show that for $d \geq 3$ (spheres), if the interaction graph is connected and $φ$ is increasing and convex, then the system synchronizes. We give a separate proof of this result. What is the situation on circles ($d=2$)? First, we show that $φ$ being increasing and convex is no longer sufficient (even for complete graphs). Then we identify a new condition under which we do have synchronization on the circle (namely, if the Taylor coefficients of $φ'$ are decreasing). As a corollary, this provide synchronization for exponential $φ$ with $β\in (0, 1]$. The proofs are based on nonconvex landscape analysis.
title Synchronization on circles and spheres with nonlinear interactions
topic Optimization and Control
Machine Learning
Dynamical Systems
url https://arxiv.org/abs/2405.18273