Particle Dynamics for Latent-Variable Energy-Based Models

• URL: http://arxiv.org/abs/2510.15447v1
• Date: Fri, 17 Oct 2025 09:04:49 GMT
• Title: Particle Dynamics for Latent-Variable Energy-Based Models
• Abstract summary: Latent-variable energy-based models (LVEBMs) assign a single normalized energy to joint pairs of observed data and latent variables.<n>We recast maximum-likelihood training as a saddle problem over distributions on the latent and joint gradients.<n>We prove existence and convergence under standard smoothness and dissipativity assumptions, with decay rates in KL divergence and Wasserstein-2 distance.
• Score: 12.84928511163926
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Latent-variable energy-based models (LVEBMs) assign a single normalized energy to joint pairs of observed data and latent variables, offering expressive generative modeling while capturing hidden structure. We recast maximum-likelihood training as a saddle problem over distributions on the latent and joint manifolds and view the inner updates as coupled Wasserstein gradient flows. The resulting algorithm alternates overdamped Langevin updates for a joint negative pool and for conditional latent particles with stochastic parameter ascent, requiring no discriminator or auxiliary networks. We prove existence and convergence under standard smoothness and dissipativity assumptions, with decay rates in KL divergence and Wasserstein-2 distance. The saddle-point view further yields an ELBO strictly tighter than bounds obtained with restricted amortized posteriors. Our method is evaluated on numerical approximations of physical systems and performs competitively against comparable approaches.

Related papers

• Particle-based Generalised Stochastic Optimisation [0.0]
  We develop a class of diffusion-based particle optimisation methods for loss functions with intractable gradients.<n>We introduce mean-field dynamics and its interacting-particle approximations, which contain several existing algorithms as special cases.<n>We show that the continuous-time particle system admits a non-asymptotic error bound.
  arXiv  Detail & Related papers  (2026-08-03T19:59:47Z)
• Disentangling Continuous-Time Latent Dynamics: Identifiability of Latent SDEs via Diffusion Shifts [60.95873409673775]
  identifiability in continuous-time latent differential equation models remains largely open.<n>We study additive-noise latent SDEs observed through an unknown nonlinear diffeomorphism.<n>We propose a two-stage estimator for latent disentanglement and optional graph recovery.
  arXiv  Detail & Related papers  (2026-06-26T16:18:28Z)
• Diffusion Flow Matching: Dimension-Improved KL Bounds and Wasserstein Guarantees [15.697611355182005]
  We provide convergence guarantees for Brownian motion based DFMs, focusing on the discretization error.<n>Our analysis is conducted under the Kullback-Leibler (KL) divergence and the 2-Wasserstein distance.
  arXiv  Detail & Related papers  (2026-06-15T12:00:13Z)
• Why SGD is not Brownian Motion: A New Perspective on Stochastic Dynamics [92.39053980710702]
  Gradient Descent (SGD) is commonly modeled as a Langevin process, assuming that minibatch noise acts as Brownian motion.<n>This approximation relies on a continuous-time limit and a sqrt(eta) noise scaling that does not match the discrete SGD update at finite learning rate.<n>We propose an alternative formulation of SGD as deterministic dynamics in a fluctuating loss landscape induced by minibatch sampling.
  arXiv  Detail & Related papers  (2026-05-21T15:50:40Z)
• Multi-Headed Transformer Architectures as Time-dependent Wasserstein Gradient Flows [16.7218879608165]
  We study the data flow in multi-headed transformer architectures as time-dependent gradient flows for a suitable interaction energy.<n>We prove the $$-convergence of the perturbed interaction energy to the unperturbed one, leading to the convergence of the corresponding gradient flows.<n>We complement these theoretical results with numerical experiments that confirm the predicted energy-dissipation identity and clarify the behavior of the dynamics in both the autonomous-like (Ornstein-Uhlenbeck) and the genuinely non-autonomous (oscillating-weights) regimes.
  arXiv  Detail & Related papers  (2026-05-15T15:32:18Z)
• Variational Smoothing and Inference for SDEs from Sparse Data with Dynamic Neural Flows [2.9746075314244376]
  We develop a novel method for smoothing the posterior differential equations (SDEs) in partially observed systems.<n>We learn this conditional score using neural networks trained to satisfy both the governing PDE and the observation-induced jump conditions.<n>The resulting score induces a posterior SDE with the same diffusion coefficient but a modified drift, enabling efficient posterior trajectory.
  arXiv  Detail & Related papers  (2026-05-07T02:47:06Z)
• GeodesicNVS: Probability Density Geodesic Flow Matching for Novel View Synthesis [54.39598154430305]
  We propose a Data-to-Data Flow Matching framework that learns deterministic transformations directly between paired views.<n>PDG-FM constrains flow trajectories using geodesic interpolants derived from probability density metrics of pretrained diffusion models.<n>These results highlight the advantages of incorporating data-dependent geometric regularization into deterministic flow matching for consistent novel view generation.
  arXiv  Detail & Related papers  (2026-03-01T09:30:11Z)
• Function-Space Decoupled Diffusion for Forward and Inverse Modeling in Carbon Capture and Storage [65.51149575007149]
  We present Fun-DDPS, a generative framework that combines function-space diffusion models with differentiable neural operator surrogates for both forward and inverse modeling.<n>Fun-DDPS produces physically consistent realizations free from the high-frequency artifacts observed in joint-state baselines.
  arXiv  Detail & Related papers  (2026-02-12T18:58:12Z)
• Weighted Stochastic Differential Equation to Implement Wasserstein-Fisher-Rao Gradient Flow [0.0]
  A promising line of work leverages tools from information geometry to augment diffusion-based samplers with mass reweighting mechanisms.<n>Our work provides a preliminary but rigorous investigation of WFR-based sampling dynamics, and aims to clarify their theoretical structure as a foundation for future developments.
  arXiv  Detail & Related papers  (2025-12-19T18:31:27Z)
• An efficient preconditioned conjugate-gradient solver for a two-component dipolar Bose-Einstein condensate [1.3037017215576174]
  We develop a preconditioned nonlinear conjugate-gradient solver for ground states of binary dipolar Bose-Einstein condensates.<n>We reproduce representative textures and droplet-stability windows reported for dipolar mixtures.
  arXiv  Detail & Related papers  (2025-10-28T15:44:47Z)
• Physics-Based Machine Learning Closures and Wall Models for Hypersonic Transition-Continuum Boundary Layer Predictions [0.21748200848556343]
  We develop a physics-constrained machine learning framework that augments transport models and boundary conditions.<n>We evaluate these for two-dimensional supersonic flat-plate flows across a range of Mach and Knudsen numbers.<n>Our results show that a trace-free anisotropic viscosity model, paired with the skewed-Gaussian distribution function wall model, achieves significantly improved accuracy.
  arXiv  Detail & Related papers  (2025-07-11T19:40:00Z)
• Spin-only dynamics of the multi-species nonreciprocal Dicke model [0.0]
  Hepp-Lieb-Dicke model is ubiquitous in cavity quantum electrodynamics.<n>We study a variation of the open Dicke model which realizes mediated nonreciprocal interactions between spin species.<n>We find signatures of phase transitions even for small system sizes.
  arXiv  Detail & Related papers  (2025-07-10T17:41:46Z)
• A Geometric Perspective on Diffusion Models [57.27857591493788]
  We inspect the ODE-based sampling of a popular variance-exploding SDE. We establish a theoretical relationship between the optimal ODE-based sampling and the classic mean-shift (mode-seeking) algorithm.
  arXiv  Detail & Related papers  (2023-05-31T15:33:16Z)
• Stochastic Interpolants: A Unifying Framework for Flows and Diffusions [18.299322342860517]
  A class of generative models that unifies flow-based and diffusion-based methods is introduced.<n>These models extend the framework proposed in Albergo and VandenEijnden (2023), enabling the use of a broad class of continuous-time processes called interpolants.
  arXiv  Detail & Related papers  (2023-03-15T17:43:42Z)
• Modeling the space-time correlation of pulsed twin beams [68.8204255655161]
  Entangled twin-beams generated by parametric down-conversion are among the favorite sources for imaging-oriented applications. We propose a semi-analytic model which aims to bridge the gap between time-consuming numerical simulations and the unrealistic plane-wave pump theory.
  arXiv  Detail & Related papers  (2023-01-18T11:29:49Z)
• Sufficient condition for gapless spin-boson Lindbladians, and its connection to dissipative time-crystals [64.76138964691705]
  We discuss a sufficient condition for gapless excitations in the Lindbladian master equation for collective spin-boson systems. We argue that gapless modes can lead to persistent dynamics in the spin observables with the possible formation of dissipative time-crystals.
  arXiv  Detail & Related papers  (2022-09-26T18:34:59Z)
• Counting Phases and Faces Using Bayesian Thermodynamic Integration [77.34726150561087]
  We introduce a new approach to reconstruction of the thermodynamic functions and phase boundaries in two-parametric statistical mechanics systems. We use the proposed approach to accurately reconstruct the partition functions and phase diagrams of the Ising model and the exactly solvable non-equilibrium TASEP.
  arXiv  Detail & Related papers  (2022-05-18T17:11:23Z)
• Feedback-induced instabilities and dynamics in the Jaynes-Cummings model [62.997667081978825]
  We investigate the coherence and steady-state properties of the Jaynes-Cummings model subjected to time-delayed coherent feedback. The introduced feedback qualitatively modifies the dynamical response and steady-state quantum properties of the system.
  arXiv  Detail & Related papers  (2020-06-20T10:07:01Z)

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.