Dimension-Uniform Discretization Analysis of Preconditioned Annealed Langevin Dynamics for Multimodal Gaussian Mixtures

• URL: http://arxiv.org/abs/2605.16473v1
• Date: Fri, 15 May 2026 15:18:32 GMT
• Title: Dimension-Uniform Discretization Analysis of Preconditioned Annealed Langevin Dynamics for Multimodal Gaussian Mixtures
• Abstract summary: Discretization is a typical source of such errors, and preconditioning with a suitable spectral decay is one way to control their accumulation.<n>We study this problem for preconditioned annealed Langevin dynamics (ALD) applied to Gaussian mixtures.
• Score: 10.631439631816166
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Obtaining stable diffusion-based samplers in high- and infinite-dimensional settings is challenging because errors can accumulate across high-frequency coordinates and make the dynamics unstable under refinement of the finite-dimensional approximation of the underlying function-space problem. Discretization is a typical source of such errors, and preconditioning with a suitable spectral decay is one way to control their accumulation. In this paper, we study this problem for preconditioned annealed Langevin dynamics (ALD) applied to Gaussian mixtures. We first show that Euler-Maruyama (EM) discretization, by treating the stiff linear part of the annealed score with a forward Euler step, imposes a stability constraint coupling the preconditioner with the annealed covariance scale. Together with the conditions ensuring dimension-uniform control of the annealed dynamics, this constraint forces the initial smoothed law to remain uniformly close to the target across dimensions. We then consider an exponential-integrator scheme that integrates the stiff linear part of the annealed score exactly. Under explicit spectral summability conditions coupling the smoothing covariance, the component covariance spectra, and the preconditioner, we prove a dimension-uniform Kullback-Leibler (KL) bound for this scheme. This bound can be made arbitrarily small, uniformly in dimension, by allowing enough time for annealing and then refining the time mesh accordingly. Importantly, these conditions allow regimes in which the KL divergence between the target and the initial smoothed law diverges with dimension, showing that the restrictions imposed by EM are scheme-dependent rather than intrinsic to ALD.

Related papers

• Dynamical zero modes, boundary dependence, and numerical instability in dynamical quantum phase transitions [5.848808787058277]
  We show that boundary dependence is encoded in dynamical zero modes (DZMs) of the Loschmidt matrix.<n>These modes carry the boundary-dependent contribution: removing them from the open-boundary LRF recovers the periodic-boundary result.<n>We show that these DZMs lead to finite-precision numerical instability, since their finite-size singular values decay exponentially with system size.
  arXiv  Detail & Related papers  (2026-07-03T15:51:04Z)
• A Quantitative Approximation Framework for Flow Distillation in Diffusion Models [9.704954388992892]
  Local approximation errors can be strongly amplified in low-noise multimodal regimes.<n>We show that deep residual compositions efficiently approximate the long-horizon transport.<n>Experiments support the prediction and reduce end-to-end relative MSE by up to 51.9% with 8 segments compared with uniform grids.
  arXiv  Detail & Related papers  (2026-06-02T16:00:43Z)
• Homogenized Transformers [5.290251602267728]
  We study a random model of deep multi-head self-attention in which the weights are resampled independently across layers and heads.<n>We prove that, under suitable joint scalings of the depth, the residual step size, and the number of heads, this dynamics admits a nontrivialed limit.
  arXiv  Detail & Related papers  (2026-04-02T12:39:27Z)
• Stability and Generalization of Push-Sum Based Decentralized Optimization over Directed Graphs [55.77845440440496]
  Push-based decentralized communication enables optimization over communication networks, where information exchange may be asymmetric.<n>We develop a unified uniform-stability framework for the Gradient Push (SGP) algorithm.<n>A key technical ingredient is an imbalance-aware generalization bound through two quantities.
  arXiv  Detail & Related papers  (2026-02-24T05:32:03Z)
• Dimension-Free Multimodal Sampling via Preconditioned Annealed Langevin Dynamics [10.631439631816166]
  Annealed Langevin dynamics (ALD) is a widely used alternative to classical Langevin since it often yields much faster mixing on multimodal targets.<n>We help bridge this gap by providing a uniform-in-dimension analysis of continuous-time ALD for multimodal targets.
  arXiv  Detail & Related papers  (2026-02-01T21:37:33Z)
• Adaptive Annealed Importance Sampling with Constant Rate Progress [68.8204255655161]
  Annealed Importance Sampling (AIS) synthesizes weighted samples from an intractable distribution. We propose the Constant Rate AIS algorithm and its efficient implementation for $alpha$-divergences.
  arXiv  Detail & Related papers  (2023-06-27T08:15:28Z)
• Convergence of mean-field Langevin dynamics: Time and space discretization, stochastic gradient, and variance reduction [49.66486092259376]
  The mean-field Langevin dynamics (MFLD) is a nonlinear generalization of the Langevin dynamics that incorporates a distribution-dependent drift. Recent works have shown that MFLD globally minimizes an entropy-regularized convex functional in the space of measures. We provide a framework to prove a uniform-in-time propagation of chaos for MFLD that takes into account the errors due to finite-particle approximation, time-discretization, and gradient approximation.
  arXiv  Detail & Related papers  (2023-06-12T16:28:11Z)
• Optimal control for state preparation in two-qubit open quantum systems driven by coherent and incoherent controls via GRAPE approach [77.34726150561087]
  We consider a model of two qubits driven by coherent and incoherent time-dependent controls. The dynamics of the system is governed by a Gorini-Kossakowski-Sudarshan-Lindblad master equation. We study evolution of the von Neumann entropy, purity, and one-qubit reduced density matrices under optimized controls.
  arXiv  Detail & Related papers  (2022-11-04T15:20:18Z)
• On optimization of coherent and incoherent controls for two-level quantum systems [77.34726150561087]
  This article considers some control problems for closed and open two-level quantum systems. The closed system's dynamics is governed by the Schr"odinger equation with coherent control. The open system's dynamics is governed by the Gorini-Kossakowski-Sudarshan-Lindblad master equation.
  arXiv  Detail & Related papers  (2022-05-05T09:08:03Z)
• On the Convergence of Stochastic Extragradient for Bilinear Games with Restarted Iteration Averaging [96.13485146617322]
  We present an analysis of the ExtraGradient (SEG) method with constant step size, and present variations of the method that yield favorable convergence. We prove that when augmented with averaging, SEG provably converges to the Nash equilibrium, and such a rate is provably accelerated by incorporating a scheduled restarting procedure.
  arXiv  Detail & Related papers  (2021-06-30T17:51:36Z)
• Towards quantum simulation of Sachdev-Ye-Kitaev model [5.931069258860319]
  We study a simplified version of the Sachdev-Ye-Kitaev (SYK) model with real interactions by exact diagonalization. A quantum phase transition from a chaotic state to an integrable state is observed by increasing the discrete separation.
  arXiv  Detail & Related papers  (2020-03-03T14:18:07Z)
• Exactly Thermalised Quantum Dynamics of the Spin-Boson Model coupled to a Dissipative Environment [0.0]
  We describe the dynamics of an exactly thermalised open quantum system coupled to a non-Markovian harmonic environment. We develop a number of competing ESLN variants designed to reduce the numerical divergence of the trace of the open system density matrix. We consider evolution under a fixed Hamiltonian and show that the system either remains in, or approaches, the correct canonical equilibrium state at long times.
  arXiv  Detail & Related papers  (2020-02-18T16:30:14Z)

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.