1 July 2024 in Chaos: An Interdisciplinary Journal of Nonlinear Science
This work advances the understanding of oscillator Ising machines (OIMs) as a nonlinear dynamic system for solving computationally hard problems. Specifically, we classify the infinite number of all possible equilibrium points of an OIM, including non-0/π ones, into three types based on their structural stability properties. We then employ the stability analysis techniques from control theory to analyze the stability property of all possible equilibrium points and obtain the necessary and sufficient condition for their stability. As a result of these analytical results, we establish, for the first time, the threshold of the binarization in terms of the coupling strength and strength of the second harmonic signal. Furthermore, we provide an estimate of the domain of attraction of each asymptotically stable equilibrium point by employing the Lyapunov stability theory. Finally, we illustrate our theoretical conclusions by numerical simulation.
9 March 2026 in Physical Review E
We propose a neural network model, which, with appropriate assignment of the stability of its equilibrium points (EPs), achieves Hopfield-like associative memory. The oscillator Ising machine (OIM), based on Kuramoto-like dynamics, is an ideal candidate for such a model, as all its 0/π binary EPs are structurally stable with their dynamic stability tunable by the coupling weights. Traditional Hopfield-based models store the desired patterns by designing the coupling weights between neurons. The design of coupling weights should simultaneously take into account both the existence and the dynamic stability of the EPs for the storage of the desired patterns. For OIMs, since all 0/π binary EPs are structurally stable, that is, any of these EPs remains an EP regardless of the values of the coupling weights or the system parameters, the design of the coupling weights needs only to focus on assigning appropriate dynamic stability for the 0/π binary EPs according to the desired patterns. In this paper, we establish a connection between the stability and the Hamiltonian energy of EPs for OIMs, and, based on this connection, provide a Hamiltonian-regularized eigenvalue contrastive method (HRECM) to train the coupling weights of OIMs for assigning appropriate stability to their EPs. Finally, numerical experiments are performed to validate the effectiveness of the proposed method.
15 April 2025 in Physical Review E
Many combinatorial optimization problems (COPs) can be mapped to Ising Hamiltonians. Oscillator Ising machines (OIMs) are built to minimize the Ising Hamiltonians, thereby indirectly solving the COPs. Specifically, the dynamics of an OIM evolve in the direction of decreasing value of the Ising Hamiltonian, and its state converges to a steady state, known as an asymptotically stable equilibrium point. Such an equilibrium point represents a candidate solution of the underlying COP. Although OIMs show great potential in solving COPs, they, like many heuristic algorithms, are prone to getting stuck in local minima. Even for trivial problems, e.g., unfrustrated Ising Hamiltonians, an OIM may get trapped in local minima if its parameters and its initial condition are not properly selected. In this work, we examine the impacts of the graph structure underlying an OIM on the computational properties of the OIM. In particular, we identify graph structures of OIMs for which the parameters of the OIMs can be properly designed such that only the equilibrium points representing global minima are asymptotically stable and all other equilibrium points are unstable. Thus, an OIM with such a graph structure, possibly with a small perturbation, can converge to the globally optimal solutions from any initial condition.
1 October 2025 in IEEE Transactions on Neural Networks and Learning Systems
Dynamic behaviors of the classical Kuramoto models have been widely studied. The dynamics of the all-to-all connected oscillator Ising machines (OIMs) is similar to that of the classical Kuramoto models, with the main difference being that there is an additional term in OIMs, called the second harmonic term. However, the dynamic behavior of an all-to-all connected OIM is significantly different and its intricate properties are largely unexplored. In this article, we study in detail the properties of the all-to-all connected OIMs and explore their application as associative memory. The number of patterns such an OIM can store increases exponentially with respect to the number of oscillators. To improve the performance of the OIMs for associative memory, we propose a new harmonic term so that the resulting OIM achieves pattern retrieval with high accuracy in the presence of a high level of noise.
20 February 2025 in TechRxiv
Dynamic behaviors of the classical Kuramoto models have been widely studied. The dynamics of the all-to-all connected oscillator Ising machines (OIMs) is similar to that of the classical Kuramoto models, with the main difference being that there is an additional term in OIMs, called the second harmonic term. However, the dynamic behavior of an all-toall connected OIM is significantly different and its intricate properties are largely unexplored. In this paper, we study in detail the properties of the the all-to-all connected OIMs and explore their application as associative memory. The number of patterns such an OIM can store increases exponentially with respect to the number of oscillators. To improve the performance of the OIMs for associative memory, we propose new harmonic term so that the resulting OIM achieves pattern retrieval with high accuracy in the presence of a high level of noise.