mlsanityData to 14 Oct 2026

Optimizing Energy-based Neural Network Training with Coherent Ising Machine

arXiv 2606.09117 ↗First posted 8 Jun 2026cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

While Ising machines serve as advanced physical solvers for the Ising model,enabling applications in combinatorial optimization and neural network training,their scalability for large-scale neural networks remains constrained by hardware connectivity limitations and suboptimal training methodologies. In this work,we leverage a Coherent Ising Machine (CIM) to train an energy-based neural network using Equilibrium Propagation, achieving performance comparable to existing software-based implementations. We further enhance the algorithm by integrating the Adam optimizer to solve for the ground state of a Hopfield energy network, significantly improving convergence speed and solution accuracy. Additionally, we demonstrate the scalability of our approach across deeper network architectures and convolutional operations. Our results highlight the potential of CIM dynamics as a scalable platform for training complex neural networks, offering a pathway toward energy-efficient implementations via analog circuits, optoelectronics, or integrated photonics. This work establishes a novel physical framework for next-generation AI hardware development.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 23 of its 60 references that are in the map. First posted on arXiv 8 Jun 2026.

Builds on

23 of 60 references.

References · 23

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2021Carbon Emissions and Large Neural Network Trainingcited by 567
  4. 2018All-Optical Machine Learning Using Diffractive Deep Neural Networkscited by 177
  5. 2019Efficient Learning for Deep Quantum Neural Networkscited by 161
  6. 2021Deep physical neural networks enabled by a backpropagation algorithm for arbitrary physical systemscited by 128
  7. 2020Scaling Equilibrium Propagation to Deep ConvNets by Drastically Reducing its Gradient Estimator Biascited by 64
  8. 2020Training End-to-End Analog Neural Networks with Equilibrium Propagationcited by 63
  9. 2018Training of photonic neural networks through in situ backpropagationcited by 45
  10. 2022Experimentally realized in situ backpropagation for deep learning in nanophotonic neural networkscited by 44
  11. 2015Application of Quantum Annealing to Training of Deep Neural Networkscited by 37
  12. 2019Updates of Equilibrium Prop Match Gradients of Backprop Through Time in an RNN with Static Inputcited by 33
11 more
  1. 2019Support vector machines on the D-Wave quantum annealercited by 33
  2. 2017Equivalence of Equilibrium Propagation and Recurrent Backpropagationcited by 32
  3. 2023Training an Ising Machine with Equilibrium Propagationcited by 29
  4. 2023Training Deep Boltzmann Networks with Sparse Ising Machinescited by 24
  5. 2024Training Coupled Phase Oscillators as a Neuromorphic Platform using Equilibrium Propagationcited by 16
  6. 2021Training Dynamical Binary Neural Networks with Equilibrium Propagationcited by 13
  7. 2021Noise-injected analog Ising machines enable ultrafast statistical sampling and machine learningcited by 11
  8. 2019Quantum-inspired annealers as Boltzmann generators for machine learning and statistical physicscited by 4
  9. 2023Low-rank combinatorial optimization and statistical learning by spatial photonic Ising machinecited by 4
  10. 2022Combinatorial optimization solving by coherent Ising machines based on spiking neural networkscited by 3
  11. 2023Training Multi-layer Neural Networks on Ising Machinecited by 3

Built on by

Not cited yet.