Mean-Field Oscillator Ising Machines: Gradient Flows and Classification of Limit Solutions
Abstract
Oscillator Ising Machines (OIMs) have emerged as promising computational architectures for approximating solutions to combinatorial optimization problems. We derive and analyze the mean-field limit of an OIM model and show that it inherits the gradient flow structure of the finite-dimensional dynamics. We identify conditions under which this mean-field evolution admits an Eulerian formulation as a gradient flow on the Wasserstein space of probability measures and contrast this with a Lagrangian formulation which is always available. This gradient flow structure strongly constrains the long-time dynamics and enables a complete classification of limit solutions and their stability in the totally symmetric case. In particular, all limit solutions are fixed points whose phases cluster into at most four groups, and for almost all parameter values, only binarized fixed points -- those with clusters at $0$ and/or π -- can be stable. Since binarized states are exactly those for which a feasible solution to the original problem can be read out, this shows that feasible solutions can almost always be recovered. We provide tight bounds on the parameter thresholds for which fixed points in this binarized family are stable, thereby identifying the threshold for binarization in this model, and present numerical evidence that the mean-field model correctly predicts behavioral regimes in certain large random networks, including Erdős-Rényi networks. Moreover, this problem provides a case study in the application of mean-field models, gradient flows, and optimal transport to the study of large-scale systems, and we highlight a number of features of this problem which are informative in this respect.
Related
- Existence and classification of solutions for singular 1-Laplacian equations with gradient terms
- Label-Permutation Symmetry and Stability in Oscillator Potts Machines
- Support Vector Machines for Classification, Regression, and Outlier Detection: A Tutorial
- Diffusion stabilises time-periodic solutions in conservation laws coupled to a relaxation oscillator
- Cross-validated feature selection using least-squares support vector machines for binary classification
BibTeX
@misc{venkatakrishnan2026meanfield,
title = {{Mean-Field Oscillator Ising Machines: Gradient Flows and Classification of Limit Solutions}},
author = {Arvind R. Venkatakrishnan and Max Emerick and Bassam Bamieh and Francesco Bullo},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2608.16025},
eprint = {2608.16025},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2608.16025},
}
RIS
TY - UNPB
TI - Mean-Field Oscillator Ising Machines: Gradient Flows and Classification of Limit Solutions
AU - Arvind R. Venkatakrishnan
AU - Max Emerick
AU - Bassam Bamieh
AU - Francesco Bullo
PY - 2026
DA - 2026/10/09
PB - arXiv
DO - 10.48550/arxiv.2608.16025
UR - https://arxiv.org/abs/2608.16025
AB - Oscillator Ising Machines (OIMs) have emerged as promising computational architectures for approximating solutions to combinatorial optimization problems. We derive and analyze the mean-field limit of an OIM model and show that it inherits the gradient flow structure of the finite-dimensional dynamics. We identify conditions under which this mean-field evolution admits an Eulerian formulation as a gradient flow on the Wasserstein space of probability measures and contrast this with a Lagrangian formulation which is always available. This gradient flow structure strongly constrains the long-time dynamics and enables a complete classification of limit solutions and their stability in the totally symmetric case. In particular, all limit solutions are fixed points whose phases cluster into at most four groups, and for almost all parameter values, only binarized fixed points -- those with clusters at $0$ and/or π -- can be stable. Since binarized states are exactly those for which a feasible solution to the original problem can be read out, this shows that feasible solutions can almost always be recovered. We provide tight bounds on the parameter thresholds for which fixed points in this binarized family are stable, thereby identifying the threshold for binarization in this model, and present numerical evidence that the mean-field model correctly predicts behavioral regimes in certain large random networks, including Erdős-Rényi networks. Moreover, this problem provides a case study in the application of mean-field models, gradient flows, and optimal transport to the study of large-scale systems, and we highlight a number of features of this problem which are informative in this respect.
ER -