Learning at the Speed of Physics: Equilibrium Propagation on Oscillator Ising Machines
This work addresses the bottleneck of implementing energy-based models on conventional processors by enabling fast, energy-efficient neuromorphic learning on physical hardware, though it appears incremental as it builds on existing Equilibrium Propagation and OIM concepts.
The paper tackled the problem of accelerating machine learning by using physical systems like Oscillator Ising Machines (OIMs) to perform optimization and sampling, achieving competitive accuracies of ~97.2% on MNIST and ~88.0% on Fashion-MNIST while maintaining robustness under hardware constraints.
Physical systems that naturally perform energy descent offer a direct route to accelerating machine learning. Oscillator Ising Machines (OIMs) exemplify this idea: their GHz-frequency dynamics mirror both the optimization of energy-based models (EBMs) and gradient descent on loss landscapes, while intrinsic noise corresponds to Langevin dynamics - supporting sampling as well as optimization. Equilibrium Propagation (EP) unifies these processes into descent on a single total energy landscape, enabling local learning rules without global backpropagation. We show that EP on OIMs achieves competitive accuracy ($\sim 97.2 \pm 0.1 \%$ on MNIST, $\sim 88.0 \pm 0.1 \%$ on Fashion-MNIST), while maintaining robustness under realistic hardware constraints such as parameter quantization and phase noise. These results establish OIMs as a fast, energy-efficient substrate for neuromorphic learning, and suggest that EBMs - often bottlenecked by conventional processors - may find practical realization on physical hardware whose dynamics directly perform their optimization.