Generative Models on Analog Hardware with Dynamics

• URL: http://arxiv.org/abs/2606.27294v1
• Date: Thu, 25 Jun 2026 17:13:00 GMT
• Title: Generative Models on Analog Hardware with Dynamics
• Abstract summary: Modern generative models assume flexible, software-defined dynamics, whereas analog hardware imposes fixed, physics-determined differential equations with limited approximation capacity.<n>This paper introduces Analog Interaction Systems, a unified framework for hardware-implementable dynamical systems.<n>A Wasserstein GAN training procedure is developed to enable training of these models without requiring them to follow a specific trajectory.
• Score: 1.1602089225841632
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Analog hardware platforms such as coupled oscillators and Analog Ising Machines naturally solve differential equations at a fraction of the energy cost of digital computation, making them attractive for low-power generative modeling, yet a fundamental mismatch exists: modern generative models assume flexible, software-defined dynamics, whereas analog hardware imposes fixed, physics-determined differential equations with limited approximation capacity. This paper introduces Analog Interaction Systems (AIS), a unified framework for hardware-implementable dynamical systems, and empirically characterizes their expressivity gap relative to neural network baselines. Two hardware-compatible mechanisms are proposed to narrow this gap - time-varying piecewise parameters and hidden physical states - and a Wasserstein GAN training procedure is developed to enable training of these models without requiring them to follow a specific trajectory. We characterize how area and power scale with connection density and precision, showing that sparse connectivity and low-bit-width quantized parameters are necessary for practical implementation, and estimate an energy cost of 23uJ per generated image for the chosen architecture, representing a 2-orders-of-magnitude improvement over digital baselines. On MNIST and Fashion-MNIST, our oscillator-based AIS achieves FID scores of 27.6 and 80.8, outperforming the best prior hardware-implementable analog generative models by 3-4x with a 4-bit sparse architecture.

Related papers

• Unlocking High-Fidelity Analog Joint Source-Channel Coding on Standard Digital Transceivers [54.82164616081277]
  D2AJSCC is a novel framework enabling high-fidelity analog J SCC deployment on standard digital PHYs.<n>Our system achieves near-ideal analog J SCC performance with graceful degradation across SNR conditions.<n>By enabling next-generation semantic transmission on legacy infrastructure without hardware modification, our framework promotes sustainable network evolution.
  arXiv  Detail & Related papers  (2026-03-10T01:42:23Z)
• Dense Associative Memories with Analog Circuits [4.0086293309536405]
  We propose a general method for building analog accelerators for DenseAMs.<n>We find that analog DenseAM hardware performs inference in constant time independent of model size.<n>We estimate lower bounds on the achievable time constants imposed by amplifier specifications, suggesting that even conservative existing analog technology can enable inference times on the order of tens to hundreds of nanoseconds.
  arXiv  Detail & Related papers  (2025-12-17T01:22:44Z)
• Hardware-Aware Model Design and Training of Silicon-based Analog Neural Networks [33.83993649730681]
  We show that by retraining the neural network using a physics-informed hardware-aware model one can fully recover the inference accuracy of the ideal network model.<n>This is more promising for scalability and integration density than the default option of improving the fidelity of the analog neural network.
  arXiv  Detail & Related papers  (2025-12-08T10:11:13Z)
• Adaptive Mesh-Quantization for Neural PDE Solvers [51.26961483962011]
  Graph Neural Networks can handle the irregular meshes required for complex geometries and boundary conditions, but still apply uniform computational effort across all nodes.<n>We propose Adaptive Mesh Quantization: spatially adaptive quantization across mesh node, edge, and cluster features, dynamically adjusting the bit-width used by a quantized model.<n>We demonstrate our framework's effectiveness by integrating it with two state-of-the-art models, MP-PDE and GraphViT, to evaluate performance across multiple tasks.
  arXiv  Detail & Related papers  (2025-11-23T14:47:24Z)
• Unlocking Out-of-Distribution Generalization in Dynamics through Physics-Guided Augmentation [46.40087254928057]
  We present SPARK, a physics-guided quantitative augmentation plugin.<n>Experiments on diverse benchmarks demonstrate that SPARK significantly outperforms state-of-the-art baselines.
  arXiv  Detail & Related papers  (2025-10-28T09:30:35Z)
• Learning High-dimensional Ionic Model Dynamics Using Fourier Neural Operators [0.0]
  We investigate whether Fourier Neural Operators can learn the evolution of all the state variables within ionic systems in higher dimensions.<n>We demonstrate the effectiveness of this approach by accurately learning the dynamics of three well-established ionic models with increasing dimensionality.<n>Both constrained and unconstrained architectures achieve comparable results in terms of accuracy across all the models considered.
  arXiv  Detail & Related papers  (2025-05-20T07:37:03Z)
• Physics Encoded Blocks in Residual Neural Network Architectures for Digital Twin Models [2.8720819157502344]
  Physics Informed Machine Learning has emerged as a popular approach for modeling and simulation in digital twins.<n>This paper presents a generic approach based on a novel physics-encoded residual neural network architecture.<n>Our method integrates differentiable physics blocks-implementing mathematical operators from physics-based models with feed-forward learning blocks.
  arXiv  Detail & Related papers  (2024-11-18T11:58:20Z)
• Automatically Learning Hybrid Digital Twins of Dynamical Systems [56.69628749813084]
  Digital Twins (DTs) simulate the states and temporal dynamics of real-world systems. DTs often struggle to generalize to unseen conditions in data-scarce settings. In this paper, we propose an evolutionary algorithm ($textbfHDTwinGen$) to autonomously propose, evaluate, and optimize HDTwins.
  arXiv  Detail & Related papers  (2024-10-31T07:28:22Z)
• A Realistic Simulation Framework for Analog/Digital Neuromorphic Architectures [73.65190161312555]
  ARCANA is a software spiking neural network simulator designed to account for the properties of mixed-signal neuromorphic circuits.<n>We show how the results obtained provide a reliable estimate of the behavior of the spiking neural network trained in software, once deployed in hardware.
  arXiv  Detail & Related papers  (2024-09-23T11:16:46Z)
• Towards training digitally-tied analog blocks via hybrid gradient computation [1.800676987432211]
  We introduce Feedforward-tied Energy-based Models (ff-EBMs) We derive a novel algorithm to compute gradients end-to-end in ff-EBMs by backpropagating and "eq-propagating" through feedforward and energy-based parts respectively. Our approach offers a principled, scalable, and incremental roadmap to gradually integrate self-trainable analog computational primitives into existing digital accelerators.
  arXiv  Detail & Related papers  (2024-09-05T07:22:19Z)
• Capturing dynamical correlations using implicit neural representations [85.66456606776552]
  We develop an artificial intelligence framework which combines a neural network trained to mimic simulated data from a model Hamiltonian with automatic differentiation to recover unknown parameters from experimental data. In doing so, we illustrate the ability to build and train a differentiable model only once, which then can be applied in real-time to multi-dimensional scattering data.
  arXiv  Detail & Related papers  (2023-04-08T07:55:36Z)
• Real-time Neural-MPC: Deep Learning Model Predictive Control for Quadrotors and Agile Robotic Platforms [59.03426963238452]
  We present Real-time Neural MPC, a framework to efficiently integrate large, complex neural network architectures as dynamics models within a model-predictive control pipeline. We show the feasibility of our framework on real-world problems by reducing the positional tracking error by up to 82% when compared to state-of-the-art MPC approaches without neural network dynamics.
  arXiv  Detail & Related papers  (2022-03-15T09:38:15Z)

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.