A Constrained Kuramoto Gradient-Flow System Can Perform High-Accuracy Finite-Time Inference
Abstract
A central question in physical inference is whether strongly constrained dynamical systems can realize accurate input--output maps through their own finite-time evolution. We study this question in Kuramoto phase networks, whose deterministic dynamics form an input-conditioned gradient flow and whose predictions are read directly from output oscillators. As a constructive training approach, we develop a two-stage teacher--student procedure. A neural teacher is first converted into an explicit phase trajectory whose terminal oscillator activations reproduce the teacher outputs, and the Kuramoto parameters are trained by matching the student vector field along this prescribed path. Because accurate teacher-forced path matching does not ensure accurate autonomous inference, we then differentiate through the autonomous finite-time rollout and directly align its terminal output with the neural target. The resulting oscillator system, with $74$ oscillators, reaches mean test accuracies of 96.711% on MNIST and 86.399% on Fashion-MNIST. This capability persists across neural-teacher architectures, matched system sizes, thermal perturbations, and integration-grid refinement. Together, these results provide a constructive demonstration that a strongly constrained, small-sized Kuramoto gradient-flow system can be trained for high-accuracy finite-time inference through a direct oscillator readout.
Related
- Noisy Pipelines I: An end-to-end pipeline to perform multivariate noise inference for LISA
- Physics-Constrained Symbolic Regression for Mean-Velocity and Mixing-Length Scaling in Zero-Pressure-Gradient Turbulent Boundary Layers
- When Information Is Not Enough: Accuracy-Constrained Thermodynamic Costs of Binary Classification
- Constrained functional priors for Bayesian inference of hot QCD matter
- Physics-Constrained Modeling and Inference of the Equation of State for Dissociative Materials
BibTeX
@misc{cheng2026constrained,
title = {{A Constrained Kuramoto Gradient-Flow System Can Perform High-Accuracy Finite-Time Inference}},
author = {Yi Cheng and Zongli Lin},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.01539},
eprint = {2609.01539},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.01539},
}
RIS
TY - UNPB
TI - A Constrained Kuramoto Gradient-Flow System Can Perform High-Accuracy Finite-Time Inference
AU - Yi Cheng
AU - Zongli Lin
PY - 2026
DA - 2026/09/01
PB - arXiv
DO - 10.48550/arxiv.2609.01539
UR - https://arxiv.org/abs/2609.01539
AB - A central question in physical inference is whether strongly constrained dynamical systems can realize accurate input--output maps through their own finite-time evolution. We study this question in Kuramoto phase networks, whose deterministic dynamics form an input-conditioned gradient flow and whose predictions are read directly from output oscillators. As a constructive training approach, we develop a two-stage teacher--student procedure. A neural teacher is first converted into an explicit phase trajectory whose terminal oscillator activations reproduce the teacher outputs, and the Kuramoto parameters are trained by matching the student vector field along this prescribed path. Because accurate teacher-forced path matching does not ensure accurate autonomous inference, we then differentiate through the autonomous finite-time rollout and directly align its terminal output with the neural target. The resulting oscillator system, with $74$ oscillators, reaches mean test accuracies of 96.711% on MNIST and 86.399% on Fashion-MNIST. This capability persists across neural-teacher architectures, matched system sizes, thermal perturbations, and integration-grid refinement. Together, these results provide a constructive demonstration that a strongly constrained, small-sized Kuramoto gradient-flow system can be trained for high-accuracy finite-time inference through a direct oscillator readout.
ER -