Hybridizing Equilibrium Propagation with Ising Machines for Efficient Energy-Based Learning

• URL: http://arxiv.org/abs/2606.09112v1
• Date: Mon, 08 Jun 2026 07:04:57 GMT
• Title: Hybridizing Equilibrium Propagation with Ising Machines for Efficient Energy-Based Learning
• Abstract summary: We introduce an Ising-dynamics-inspired equilibrium-propagation framework in which dissipative Hopfield relaxation is replaced by an extended phase-space dynamics with conjugate variables.<n>We show that this dynamics lowers effective energy barriers, accelerates convergence, improves noise, and trains deep convolutional Hopfield networks on MNIST, FashionMNIST, and CIFAR-10 with performance comparable to backpropagation.
• Score: 16.985188733863602
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The rapid evolution of artificial intelligence has led to substantial advances in deep neural networks. Nonetheless, conventional GPU-based training remains highly energy-demanding, motivating the exploration of physical dynamics and compatible energy-based learning schemes, such as equilibrium propagation (EP). EP-based training, however, frequently suffers from convergence to local minima due to phase-space contraction. Here we introduce an Ising-dynamics-inspired equilibrium-propagation framework in which dissipative Hopfield relaxation is replaced by an extended phase-space dynamics with conjugate variables. The resulting training paradigm keeps the local two-phase learning rule of EP while changing the physical route by which neural states reach equilibrium. We show that this dynamics lowers effective energy barriers, accelerates convergence, improves noise robustness, and trains deep convolutional Hopfield networks on MNIST, FashionMNIST, and CIFAR-10 with performance comparable to backpropagation.

Related papers

• EPIC-CIM: Training Convolutional Neural Networks on a Coherent Ising Machine via Equilibrium Propagation [37.18820527520441]
  Quantum convolutional neural networks, due to the involvement of quantum measurements and discrete quantum state evolution, face inherent training challenges.<n>In this framework, input data are processed through convolutional operations, followed by quantum sampling to generate binary representations.<n>The overall network energy is composed of convolutional feature matching terms, linear coupling terms at the output layer, and global output constraint terms.
  arXiv  Detail & Related papers  (2026-07-08T02:46:41Z)
• Controlled Dynamics Attractor Transformer [58.15454173718687]
  Transformer architectures have advanced representation learning and inference in deep models through self-attention mechanisms.<n>In parallel,associative memory (AM) frameworks map representations onto energy landscapes, offering interpretable retrieval mechanisms.<n>We propose Controlled Dynamics Attractor Transformer (CCAT), which couples a mixture von Mises-Fisher (Mo-vMF) attention energy with a Hopfield refinement energy.<n>CCAT achieves state-of-the-art performance across multiple benchmarks in graph anomaly detection and graph classification.
  arXiv  Detail & Related papers  (2026-06-13T09:04:22Z)
• TIDE: Asymmetric Neural Circuits for Stabilized Temporal Inhibitory-Excitatory Dynamics [51.37317469455798]
  Recent Continuous Thought Machine architecture decouples internal computation from external inputs via neural dynamics.<n>We propose to model neural dynamics using asymmetric Excitatory-Inhibitory (E-I) networks.<n>We introduce Temporal Inhibitory-Excitatory Dynamic Engine (TIDE), a neuro-inspired architecture that computes internal representations through neural dynamics stabilized.
  arXiv  Detail & Related papers  (2026-05-19T05:59:13Z)
• Machine learning nonequilibrium phase transitions in charge-density wave insulators [3.4485371511969003]
  We develop a machine learning framework for adiabatic lattice dynamics coupled to nonequilibrium electrons.<n>Our results establish direct force learning as an efficient and accurate approach for simulating nonequilibrium lattice dynamics in driven quantum materials.
  arXiv  Detail & Related papers  (2026-01-12T14:34:50Z)
• Near-Equilibrium Propagation training in nonlinear wave systems [0.0]
  Backpropagation learning algorithm, the workhorse of modern artificial intelligence, is notoriously difficult to implement in physical neural networks.<n>We extend EP learning to both discrete and continuous complex-valued wave systems.<n> Numerical studies on standard benchmarks, including a simple logical task and handwritten-digit recognition, demonstrate stable convergence.
  arXiv  Detail & Related papers  (2025-10-17T15:03:07Z)
• Learning at the Speed of Physics: Equilibrium Propagation on Oscillator Ising Machines [0.0]
  Physical systems that naturally perform energy descent offer a direct route to machine learning.<n>We show that OIMs achieve competitive accuracy without global backpropagation.<n>These results establish OIMs as a fast, energy-efficient substrate for neuromorphic learning.
  arXiv  Detail & Related papers  (2025-10-14T19:15:49Z)
• Training Deep Normalization-Free Spiking Neural Networks with Lateral Inhibition [52.59263087086756]
  Training deep neural networks (SNNs) has critically depended on explicit normalization schemes, such as batch normalization.<n>We propose a normalization-free learning framework that incorporates lateral inhibition inspired by cortical circuits.<n>We show that our framework enables stable training of deep SNNs with biological realism and achieves competitive performance without resorting to explicit normalizations.
  arXiv  Detail & Related papers  (2025-09-27T11:11:30Z)
• Rotational Equilibrium: How Weight Decay Balances Learning Across Neural Networks [33.88586668321127]
  This study investigates how weight decay affects the update behavior of individual neurons in deep neural networks. We show that explicitly controlling the rotation provides the benefits of weight decay while substantially reducing the need for learning rate warmup.
  arXiv  Detail & Related papers  (2023-05-26T19:14:01Z)
• Scaling Equilibrium Propagation to Deep ConvNets by Drastically Reducing its Gradient Estimator Bias [62.43908463620527]
  In practice, EP does not scale to visual tasks harder than MNIST. We show that a bias in the gradient estimate of EP, inherent in the use of finite nudging, is responsible for this phenomenon. These results highlight EP as a scalable approach to compute error gradients in deep neural networks, thereby motivating its hardware implementation.
  arXiv  Detail & Related papers  (2021-01-14T10:23:40Z)
• Equilibrium Propagation with Continual Weight Updates [69.87491240509485]
  We propose a learning algorithm that bridges Machine Learning and Neuroscience, by computing gradients closely matching those of Backpropagation Through Time (BPTT) We prove theoretically that, provided the learning rates are sufficiently small, at each time step of the second phase the dynamics of neurons and synapses follow the gradients of the loss given by BPTT. These results bring EP a step closer to biology by better complying with hardware constraints while maintaining its intimate link with backpropagation.
  arXiv  Detail & Related papers  (2020-04-29T14:54:30Z)
• Continual Weight Updates and Convolutional Architectures for Equilibrium Propagation [69.87491240509485]
  Equilibrium Propagation (EP) is a biologically inspired alternative algorithm to backpropagation (BP) for training neural networks. We propose a discrete-time formulation of EP which enables to simplify equations, speed up training and extend EP to CNNs. Our CNN model achieves the best performance ever reported on MNIST with EP.
  arXiv  Detail & Related papers  (2020-04-29T12:14:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.