A general learning scheme for classical and quantum Ising machines
This work offers a novel approach for leveraging Ising machines in machine learning, potentially advancing quantum machine learning, though it appears incremental in its specific implementation.
The authors proposed a new machine learning model based on the Ising structure that can be trained using gradient descent, with partial derivatives estimated by the Ising machine itself, and presented experimental results showing new possibilities for learning tasks, including quantum applications.
An Ising machine is any hardware specifically designed for finding the ground state of the Ising model. Relevant examples are coherent Ising machines and quantum annealers. In this paper, we propose a new machine learning model that is based on the Ising structure and can be efficiently trained using gradient descent. We provide a mathematical characterization of the training process, which is based upon optimizing a loss function whose partial derivatives are not explicitly calculated but estimated by the Ising machine itself. Moreover, we present some experimental results on the training and execution of the proposed learning model. These results point out new possibilities offered by Ising machines for different learning tasks. In particular, in the quantum realm, the quantum resources are used for both the execution and the training of the model, providing a promising perspective in quantum machine learning.