Noise-injected analog Ising machines enable ultrafast statistical sampling and machine learning

Ising machines are a promising non-von-Neumann computational concept for neural network training and combinatorial optimization. However, while various neural networks can be implemented with Ising machines, their inability to perform fast statistical sampling makes them inefficient for training these neural networks compared to digital computers. Here, we introduce a universal concept to achieve ultrafast statistical sampling with Ising machines by injecting analog noise. With an opto-electronic Ising machine, we demonstrate that this can be used for accurate sampling of Boltzmann distributions and unsupervised training of neural networks, with equal accuracy as software-based training. Through simulations, we find that Ising machines can perform statistical sampling orders-of-magnitudes faster than software-based methods. This makes Ising machines into efficient tools for machine learning and other applications beyond combinatorial optimization.