Continuous Limits of Coupled Flows in Representation Learning

• URL: http://arxiv.org/abs/2604.16801v1
• Date: Sat, 18 Apr 2026 03:19:54 GMT
• Title: Continuous Limits of Coupled Flows in Representation Learning
• Abstract summary: Decentralized algorithms driven by local interactions offer a fundamental distributed alternative to global error signals.<n>We bridge this gap by formalizing decentralized learning as a coupled slow-fast dynamical system.<n>Our framework bridges discrete algorithms with continuous analysis, providing a formal theoretical baseline for decentralized representation learning.
• Score: 13.704592299911157
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: While modern representation learning relies heavily on global error signals, decentralized algorithms driven by local interactions offer a fundamental distributed alternative. However, the macroscopic convergence properties of these discrete dynamics on continuous data manifolds remain theoretically unresolved, notoriously suffering from parameter explosion. We bridge this gap by formalizing decentralized learning as a coupled slow-fast dynamical system on Riemannian manifolds. First, using measure-theoretic limits, we prove that the discrete spatial transitions converge uniformly to an overdamped Langevin stochastic differential equation. Second, via the Itô-Poisson resolvent and a stochastic extension of LaSalle's Invariance Principle, we establish that the representation weights unconditionally avoid divergence and align strictly with the principal eigenspace of the spatial measure. Finally, we construct a joint Lyapunov functional for the fully coupled spatial-parametric flow. This proves global dissipativity and demonstrates that orthogonally disentangled, linearly separable features emerge spontaneously at the stationary limit. Our framework bridges discrete algorithms with continuous stochastic analysis, providing a formal theoretical baseline for decentralized representation learning.

Related papers

• Path integral formulation of finite-dimensional quantum mechanics in discrete phase space [0.0]
  We develop a path integral representation for the dynamics of quantum systems with a finite-dimensional Hilbert space.<n>For Hamiltonians linear in the phase-space coordinates, we show that the fluctuation sum factorizes.<n>We show explicitly that the full entanglement dynamics requires the coherent contribution of all fluctuation sectors of the action.
  arXiv  Detail & Related papers  (2026-04-22T17:04:10Z)
• Latent-Variable Learning of SPDEs via Wiener Chaos [2.0901018134712297]
  We study the problem of learning the law of linear partial differential equations (SPDEs) with additive Gaussian forcing from observations.<n>Our approach combines a spectral Galerkin projection with a truncated Wiener chaos expansion, yielding a separation between evolution and forcing domains.<n>This reduces the infinite-dimensional deterministic SPDE to a finite system of parametrized ordinary differential equations governing latent temporal dynamics.
  arXiv  Detail & Related papers  (2026-02-12T10:19:43Z)
• Parallel Complex Diffusion for Scalable Time Series Generation [50.01609741902786]
  PaCoDi is a spectral-native architecture that decouples generative modeling in the frequency domain.<n>We show that PaCoDi outperforms existing baselines in both generation quality and inference speed.
  arXiv  Detail & Related papers  (2026-02-10T14:31:53Z)
• Spectral Diffusion Models on the Sphere [0.0]
  Diffusion models provide a principled framework for generative modeling via differential equations and time-reversed dynamics.<n>We develop a diffusion modeling framework defined directly on finite-dimensional harmonic representations of real-valued functions on the sphere.
  arXiv  Detail & Related papers  (2026-01-28T11:19:37Z)
• Foundations of Diffusion Models in General State Spaces: A Self-Contained Introduction [54.95522167029998]
  This article is a self-contained primer on diffusion over general state spaces.<n>We develop the discrete-time view (forward noising via Markov kernels and learned reverse dynamics) alongside its continuous-time limits.<n>A common variational treatment yields the ELBO that underpins standard training losses.
  arXiv  Detail & Related papers  (2025-12-04T18:55:36Z)
• Non-Asymptotic Convergence of Discrete Diffusion Models: Masked and Random Walk dynamics [13.202844408027412]
  We develop new and sharp convergence guarantees for three popular discrete diffusion models.<n>We show that the computational complexity of each method scales linearly in the dimension, up to logarithmic factors.<n>This study provides the first non-asymptotic convergence guarantees for these noising processes.
  arXiv  Detail & Related papers  (2025-11-29T18:24:43Z)
• Error Analysis of Discrete Flow with Generator Matching [34.847768962128164]
  We develop a unified framework grounded in calculus theory to investigate the theoretical properties of discrete flow models.<n>Specifically, we derive the KL divergence of two path measures regarding two continuous-time Markov chains with different transition rates.<n>We provide a comprehensive analysis that encompasses the error arising from transition rate estimation and early stopping.
  arXiv  Detail & Related papers  (2025-09-26T05:41:45Z)
• Overcoming Dimensional Factorization Limits in Discrete Diffusion Models through Quantum Joint Distribution Learning [79.65014491424151]
  We propose a quantum Discrete Denoising Diffusion Probabilistic Model (QD3PM)<n>It enables joint probability learning through diffusion and denoising in exponentially large Hilbert spaces.<n>This paper establishes a new theoretical paradigm in generative models by leveraging the quantum advantage in joint distribution learning.
  arXiv  Detail & Related papers  (2025-05-08T11:48:21Z)
• Convergence of Score-Based Discrete Diffusion Models: A Discrete-Time Analysis [56.442307356162864]
  We study the theoretical aspects of score-based discrete diffusion models under the Continuous Time Markov Chain (CTMC) framework.<n>We introduce a discrete-time sampling algorithm in the general state space $[S]d$ that utilizes score estimators at predefined time points.<n>Our convergence analysis employs a Girsanov-based method and establishes key properties of the discrete score function.
  arXiv  Detail & Related papers  (2024-10-03T09:07:13Z)
• Broadening Target Distributions for Accelerated Diffusion Models via a Novel Analysis Approach [49.97755400231656]
  We show that a new accelerated DDPM sampler achieves accelerated performance for three broad distribution classes not considered before.<n>Our results show an improved dependency on the data dimension $d$ among accelerated DDPM type samplers.
  arXiv  Detail & Related papers  (2024-02-21T16:11:47Z)
• Lifting the Convex Conjugate in Lagrangian Relaxations: A Tractable Approach for Continuous Markov Random Fields [53.31927549039624]
  We show that a piecewise discretization preserves better contrast from existing discretization problems. We apply this theory to the problem of matching two images.
  arXiv  Detail & Related papers  (2021-07-13T12:31:06Z)
• The Connection between Discrete- and Continuous-Time Descriptions of Gaussian Continuous Processes [60.35125735474386]
  We show that discretizations yielding consistent estimators have the property of invariance under coarse-graining' This result explains why combining differencing schemes for derivatives reconstruction and local-in-time inference approaches does not work for time series analysis of second or higher order differential equations.
  arXiv  Detail & Related papers  (2021-01-16T17:11:02Z)

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.