Mean-Field Langevin Diffusions with Density-dependent Temperature

• URL: http://arxiv.org/abs/2507.20958v1
• Date: Mon, 28 Jul 2025 16:09:57 GMT
• Title: Mean-Field Langevin Diffusions with Density-dependent Temperature
• Authors: Yu-Jui Huang, Zachariah Malik,
• Abstract summary: We study the induced density by the non-linear Lambert principle to be minimized.<n>As the Langevin dynamics is now self-regulated by its own density, it forms a mean-field differential equation.
• Score: 1.2277343096128712
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In the context of non-convex optimization, we let the temperature of a Langevin diffusion to depend on the diffusion's own density function. The rationale is that the induced density reveals to some extent the landscape imposed by the non-convex function to be minimized, such that a density-dependent temperature can provide location-wise random perturbation that may better react to, for instance, the location and depth of local minimizers. As the Langevin dynamics is now self-regulated by its own density, it forms a mean-field stochastic differential equation (SDE) of the Nemytskii type, distinct from the standard McKean-Vlasov equations. Relying on Wasserstein subdifferential calculus, we first show that the corresponding (nonlinear) Fokker-Planck equation has a unique solution. Next, a weak solution to the SDE is constructed from the solution to the Fokker-Planck equation, by Trevisan's superposition principle. As time goes to infinity, we further show that the density induced by the SDE converges to an invariant distribution, which admits an explicit formula in terms of the Lambert $W$ function.

Related papers

• Langevin SDEs have unique transient dynamics [3.5558885788605337]
  We prove that the drift and diffusion terms of a Langevin SDE are jointly identifiable from temporal marginal distributions.<n>This complete characterization of structural identifiability removes the long-standing assumption that the diffusion must be known to identify the drift.
  arXiv  Detail & Related papers  (2025-05-27T21:06:04Z)
• Exact dynamics of quantum dissipative $XX$ models: Wannier-Stark localization in the fragmented operator space [49.1574468325115]
  We find an exceptional point at a critical dissipation strength that separates oscillating and non-oscillating decay. We also describe a different type of dissipation that leads to a single decay mode in the whole operator subspace.
  arXiv  Detail & Related papers  (2024-05-27T16:11:39Z)
• AdjointDEIS: Efficient Gradients for Diffusion Models [2.0795007613453445]
  We show that continuous adjoint equations for diffusion SDEs actually simplify to a simple ODE.<n>We also demonstrate the effectiveness of AdjointDEIS for guided generation with an adversarial attack in the form of the face morphing problem.
  arXiv  Detail & Related papers  (2024-05-23T19:51:33Z)
• Fisher information dissipation for time inhomogeneous stochastic differential equations [7.076726009680242]
  We provide a Lyapunov convergence analysis for time-inhomogeneous variable coefficient differential equations. Three typical examples include overdamped, irreversible drift, and underdamped Langevin dynamics.
  arXiv  Detail & Related papers  (2024-02-01T21:49:50Z)
• Differentially Private Gradient Flow based on the Sliced Wasserstein Distance [59.1056830438845]
  We introduce a novel differentially private generative modeling approach based on a gradient flow in the space of probability measures.<n> Experiments show that our proposed model can generate higher-fidelity data at a low privacy budget.
  arXiv  Detail & Related papers  (2023-12-13T15:47:30Z)
• Deep Equilibrium Based Neural Operators for Steady-State PDEs [100.88355782126098]
  We study the benefits of weight-tied neural network architectures for steady-state PDEs. We propose FNO-DEQ, a deep equilibrium variant of the FNO architecture that directly solves for the solution of a steady-state PDE.
  arXiv  Detail & Related papers  (2023-11-30T22:34:57Z)
• Self-Consistency of the Fokker-Planck Equation [117.17004717792344]
  The Fokker-Planck equation governs the density evolution of the Ito process. Ground-truth velocity field can be shown to be the solution of a fixed-point equation. In this paper, we exploit this concept to design a potential function of the hypothesis velocity fields.
  arXiv  Detail & Related papers  (2022-06-02T03:44:23Z)
• GANs as Gradient Flows that Converge [3.8707695363745223]
  We show that along the gradient flow induced by a distribution-dependent ordinary differential equation, the unknown data distribution emerges as the long-time limit. The simulation of the ODE is shown equivalent to the training of generative networks (GANs) This equivalence provides a new "cooperative" view of GANs and, more importantly, sheds new light on the divergence of GANs.
  arXiv  Detail & Related papers  (2022-05-05T20:29:13Z)
• Stationary Density Estimation of It\^o Diffusions Using Deep Learning [6.8342505943533345]
  We consider the density estimation problem associated with the stationary measure of ergodic Ito diffusions from a discrete-time series. We employ deep neural networks to approximate the drift and diffusion terms of the SDE. We establish the convergence of the proposed scheme under appropriate mathematical assumptions.
  arXiv  Detail & Related papers  (2021-09-09T01:57:14Z)
• Mean-Square Analysis with An Application to Optimal Dimension Dependence of Langevin Monte Carlo [60.785586069299356]
  This work provides a general framework for the non-asymotic analysis of sampling error in 2-Wasserstein distance. Our theoretical analysis is further validated by numerical experiments.
  arXiv  Detail & Related papers  (2021-09-08T18:00:05Z)
• Large-Scale Wasserstein Gradient Flows [84.73670288608025]
  We introduce a scalable scheme to approximate Wasserstein gradient flows. Our approach relies on input neural networks (ICNNs) to discretize the JKO steps. As a result, we can sample from the measure at each step of the gradient diffusion and compute its density.
  arXiv  Detail & Related papers  (2021-06-01T19:21:48Z)

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.