A Blueprint for Equilibrium-Based Differentiable Continuous-Variable Thermodynamic Computing

• URL: http://arxiv.org/abs/2607.16183v1
• Date: Fri, 17 Jul 2026 17:57:49 GMT
• Title: A Blueprint for Equilibrium-Based Differentiable Continuous-Variable Thermodynamic Computing
• Abstract summary: We focus on energy-based thermodynamic computing where the process is well described by Langevin dynamics with tunable energy potentials.<n>The implementation of such potentials in physical hardware enables us to generate and sample from basic parameterized energy-based models.<n>We demonstrate how to construct and train popular classes of machine learning models based on these hardware-native energy-based models.
• Score: 0.42159389323887214
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: To address the escalating energy and latency demands of machine-learning workloads, we introduce a blueprint for an energy-efficient and fast thermodynamic computing stack that leverages stochastic analog processes in physical hardware. In this work, we focus on energy-based thermodynamic computing where the stochastic process is well described by Langevin dynamics with tunable energy potentials. The implementation of such potentials in physical hardware enables us to generate and sample from basic parameterized energy-based models. We demonstrate how to construct and train popular classes of machine learning models based on these hardware-native energy-based models, using the framework of probabilistic graphical models. We analyze the runtime and energy consumption of different models in this thermodynamic paradigm based on theoretical considerations and numerical studies. As a preliminary experimental realization of such hardware, we present our stochastic analog superconducting circuits driven by thermal noise. Together, these results outline a path toward energy-efficient thermodynamic hardware for probabilistic machine learning.

Related papers

• Thermodynamic Performance Limits for Score-Based Diffusion Models [0.0]
  We establish a connection between score-based diffusion models and non-equilibrium thermodynamics by deriving performance limits based on entropy rates.<n>Our framework connects generative modeling performance to fundamental physical principles through thermodynamics.
  arXiv  Detail & Related papers  (2025-10-07T17:35:18Z)
• Training thermodynamic computers by gradient descent [0.0]
  We show how to adjust the parameters of a thermodynamic computer by descent in order to perform a desired computation.<n>We estimate the thermodynamic advantage -- the ratio of energy costs of the digital and thermodynamic implementations -- to exceed seven orders of magnitude.
  arXiv  Detail & Related papers  (2025-09-18T18:12:55Z)
• TICA-Based Free Energy Matching for Machine-Learned Molecular Dynamics [39.146761527401424]
  We introduce a complementary energy matching term into the loss function.<n>We evaluate our framework on the Chignolin protein using the CGSchNet model.<n>While energy matching did not yield statistically significant improvements in accuracy, it revealed distinct tendencies in how models generalize the free energy surface.
  arXiv  Detail & Related papers  (2025-09-18T04:22:25Z)
• Thermodynamic bounds on energy use in Deep Neural Networks [0.0]
  We show that Deep Neural Networks (DNNs) implemented on analog physical substrates can operate under markedly different thermodynamic constraints.<n>We distinguish between two classes of analog systems: dynamic and quasi-static.<n>Our results suggest that while analog implementations can outperform digital ones during inference, the thermodynamic cost of training scales similarly in both paradigms.
  arXiv  Detail & Related papers  (2025-03-13T02:35:07Z)
• Latent Space Energy-based Neural ODEs [73.01344439786524]
  This paper introduces novel deep dynamical models designed to represent continuous-time sequences.<n>We train the model using maximum likelihood estimation with Markov chain Monte Carlo.<n> Experimental results on oscillating systems, videos and real-world state sequences (MuJoCo) demonstrate that our model with the learnable energy-based prior outperforms existing counterparts.
  arXiv  Detail & Related papers  (2024-09-05T18:14:22Z)
• Quantum Dynamics of Machine Learning [3.567107449359775]
  The quantum dynamic equation (QDE) of machine learning is obtained based on Schr"odinger equation and potential energy equivalence relationship. The relationship between quantum dynamics and thermodynamics is also established in this paper.
  arXiv  Detail & Related papers  (2024-07-07T16:30:46Z)
• Discovering Interpretable Physical Models using Symbolic Regression and Discrete Exterior Calculus [55.2480439325792]
  We propose a framework that combines Symbolic Regression (SR) and Discrete Exterior Calculus (DEC) for the automated discovery of physical models. DEC provides building blocks for the discrete analogue of field theories, which are beyond the state-of-the-art applications of SR to physical problems. We prove the effectiveness of our methodology by re-discovering three models of Continuum Physics from synthetic experimental data.
  arXiv  Detail & Related papers  (2023-10-10T13:23:05Z)
• Energy Transformer [64.22957136952725]
  Our work combines aspects of three promising paradigms in machine learning, namely, attention mechanism, energy-based models, and associative memory. We propose a novel architecture, called the Energy Transformer (or ET for short), that uses a sequence of attention layers that are purposely designed to minimize a specifically engineered energy function.
  arXiv  Detail & Related papers  (2023-02-14T18:51:22Z)
• Constructing Neural Network-Based Models for Simulating Dynamical Systems [59.0861954179401]
  Data-driven modeling is an alternative paradigm that seeks to learn an approximation of the dynamics of a system using observations of the true system. This paper provides a survey of the different ways to construct models of dynamical systems using neural networks. In addition to the basic overview, we review the related literature and outline the most significant challenges from numerical simulations that this modeling paradigm must overcome.
  arXiv  Detail & Related papers  (2021-11-02T10:51:42Z)
• On Energy-Based Models with Overparametrized Shallow Neural Networks [44.74000986284978]
  Energy-based models (EBMs) are a powerful framework for generative modeling. In this work we focus on shallow neural networks. We show that models trained in the so-called "active" regime provide a statistical advantage over their associated "lazy" or kernel regime.
  arXiv  Detail & Related papers  (2021-04-15T15:34:58Z)
• Physics-Integrated Variational Autoencoders for Robust and Interpretable Generative Modeling [86.9726984929758]
  We focus on the integration of incomplete physics models into deep generative models. We propose a VAE architecture in which a part of the latent space is grounded by physics. We demonstrate generative performance improvements over a set of synthetic and real-world datasets.
  arXiv  Detail & Related papers  (2021-02-25T20:28:52Z)

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.