Learning at the Speed of Physics: Equilibrium Propagation on Oscillator Ising Machines

• URL: http://arxiv.org/abs/2510.12934v1
• Date: Tue, 14 Oct 2025 19:15:49 GMT
• Title: Learning at the Speed of Physics: Equilibrium Propagation on Oscillator Ising Machines
• Abstract summary: 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.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Hybridizing Equilibrium Propagation with Ising Machines for Efficient Energy-Based Learning [16.985188733863602]
  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.
  arXiv  Detail & Related papers  (2026-06-08T07:04:57Z)
• PhySPRING: Structure-Preserving Reduction of Physics-Informed Twins via GNN [9.28876902600417]
  We present PhySPRING, a differentiable GNN-based method to reduce complexity in spring--mass digital twins.<n>On the PhysTwin benchmark, PhySPRING improves dense reconstruction and prediction accuracy over PhysTwin.<n>We also demonstrate the effectiveness of PhySPRING in a Real2Sim robot policy-evaluation pipeline.
  arXiv  Detail & Related papers  (2026-05-08T12:55:58Z)
• Energy-based Regularization for Learning Residual Dynamics in Neural MPC for Omnidirectional Aerial Robots [2.5784045169981336]
  We propose a novel energy-based regularization loss function which is applied to the training of a neural model.<n>Our method achieves a significantly increased flight stability implicitly due to the energy regularization and up to 15% lower MAE.
  arXiv  Detail & Related papers  (2026-04-16T06:33:33Z)
• EFF-Grasp: Energy-Field Flow Matching for Physics-Aware Dexterous Grasp Generation [54.09734511705173]
  EFF-Grasp is a Flow-Matching synthesis-based framework for physics-aware dexterous grasp generation.<n>We reformulate grasp as a deterministic ordinary differential equation (ODE) process, which enables efficient and stable generation through smooth probability flows.<n> EFF-Grasp achieves superior performance in grasp quality and physical feasibility, while requiring substantially fewer sampling steps than diffusion-based baselines.
  arXiv  Detail & Related papers  (2026-03-17T06:11:56Z)
• FastPhysGS: Accelerating Physics-based Dynamic 3DGS Simulation via Interior Completion and Adaptive Optimization [56.17833729527066]
  We propose FastPhysGS, a framework for physics-based dynamic 3DGS simulation.<n>FastPhysGS achieves high-fidelity physical simulation in 1 minute using only 7 GB runtime memory.
  arXiv  Detail & Related papers  (2026-02-02T07:00:42Z)
• Aligning Agentic World Models via Knowledgeable Experience Learning [68.85843641222186]
  We introduce WorldMind, a framework that constructs a symbolic World Knowledge Repository by synthesizing environmental feedback.<n>WorldMind achieves superior performance compared to baselines with remarkable cross-model and cross-environment transferability.
  arXiv  Detail & Related papers  (2026-01-19T17:33:31Z)
• PhyG-MoE: A Physics-Guided Mixture-of-Experts Framework for Energy-Efficient GNSS Interference Recognition [49.955269674859004]
  This paper introduces PhyG-MoE (Physics-Guided Mixture-of-Experts), a framework designed to align model capacity with signal complexity.<n>Unlike static architectures, the proposed system employs a spectrum-based gating mechanism that routes signals based on their spectral feature entanglement.<n>A high-capacity TransNeXt expert is activated on-demand to disentangle complex features in saturated scenarios, while lightweight experts handle fundamental signals to minimize latency.
  arXiv  Detail & Related papers  (2026-01-19T07:57:52Z)
• EPO: Diverse and Realistic Protein Ensemble Generation via Energy Preference Optimization [14.859985641146672]
  This paper presents Energy Preference Optimization (EPO), an online refinement that turns a pretrained protein ensemble generator into an energy-aware sampler.<n>On Tetrapeptides, ATLAS, and Fast-Folding benchmarks, EPO successfully generates diverse and physically realistic ensembles.
  arXiv  Detail & Related papers  (2025-11-13T10:25:50Z)
• Equilibrium Matching: Generative Modeling with Implicit Energy-Based Models [52.74448905289362]
  EqM is a generative modeling framework built from an equilibrium dynamics perspective.<n>By replacing time-conditional velocities with a unified equilibrium landscape, EqM offers a tighter bridge between flow and energy-based models.
  arXiv  Detail & Related papers  (2025-10-02T17:59:06Z)
• Feedback-MPPI: Fast Sampling-Based MPC via Rollout Differentiation -- Adios low-level controllers [0.9674641730446749]
  Model Predictive Path Integral control is a powerful sampling-based approach suitable for complex robotic tasks.<n>This paper introduces robust feedback gains derived from sensitivity used in gradient-based MPC.<n>We demonstrate the effectiveness of F-MPPI in simulations through real-world experiments on two robotic platforms.
  arXiv  Detail & Related papers  (2025-06-17T07:47:33Z)
• OmniFluids: Physics Pre-trained Modeling of Fluid Dynamics [25.066485418709114]
  We propose OmniFluids, a pure physics pre-trained model that captures fundamental fluid dynamics laws and adapts efficiently to diverse downstream tasks.<n>We develop a training framework combining physics-only pre-training, coarse-grid operator distillation, and few-shot fine-tuning.<n>Tests show that OmniFluids outperforms state-of-the-art AI-driven methods in terms of flow field prediction and statistics.
  arXiv  Detail & Related papers  (2025-06-12T16:23:02Z)
• A Physics-Inspired Optimizer: Velocity Regularized Adam [9.38448580878081]
  We introduce Velocity-Regularized Adamvolution (VRAdam) for training deep neural networks.<n>VRAdam adds a higher order penalty on the learning rate based on the velocity.<n>We demonstrate that VRAdam exceeds the performance against standard convexs including AdamW.
  arXiv  Detail & Related papers  (2025-05-19T14:51:40Z)
• Learning to Dissipate Energy in Oscillatory State-Space Models [51.98491034847041]
  State-space models (SSMs) are a class of networks for sequence learning.<n>We show that D-LinOSS consistently outperforms previous LinOSS methods on long-range learning tasks.
  arXiv  Detail & Related papers  (2025-05-17T23:15:17Z)
• Explore Activation Sparsity in Recurrent LLMs for Energy-Efficient Neuromorphic Computing [3.379854610429579]
  Recurrent Large Language Models (R-LLM) have proven effective in mitigating the complexity of self-attention.<n>We propose a low-cost, training-free algorithm to sparsify R-LLMs' activations to enhance energy efficiency on neuromorphic hardware.
  arXiv  Detail & Related papers  (2025-01-09T19:13:03Z)
• Neural Material Adaptor for Visual Grounding of Intrinsic Dynamics [48.99021224773799]
  We propose the Neural Material Adaptor (NeuMA), which integrates existing physical laws with learned corrections. We also propose Particle-GS, a particle-driven 3D Gaussian Splatting variant that bridges simulation and observed images.
  arXiv  Detail & Related papers  (2024-10-10T17:43:36Z)
• Overcoming systematic softening in universal machine learning interatomic potentials by fine-tuning [3.321322648845526]
  Machine learning interatomic potentials (MLIPs) have introduced a new paradigm for atomic simulations. Recent advancements have seen the emergence of universal MLIPs (uMLIPs) that are pre-trained on diverse materials datasets. We show that their performance in extrapolating to out-of-distribution complex atomic environments remains unclear.
  arXiv  Detail & Related papers  (2024-05-11T22:30:47Z)

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.