Geometric regularization of autoencoders via observed stochastic dynamics

• URL: http://arxiv.org/abs/2604.16282v1
• Date: Fri, 17 Apr 2026 17:44:02 GMT
• Title: Geometric regularization of autoencoders via observed stochastic dynamics
• Abstract summary: Local-chart methods like ATLAS suffer from exponential landmark scaling and per-step reprojection.<n>Autoencoder alternatives leave tangent tangent geometry poorly constrained.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Stochastic dynamical systems with slow or metastable behavior evolve, on long time scales, on an unknown low-dimensional manifold in high-dimensional ambient space. Building a reduced simulator from short-burst ambient ensembles is a long-standing problem: local-chart methods like ATLAS suffer from exponential landmark scaling and per-step reprojection, while autoencoder alternatives leave tangent-bundle geometry poorly constrained, and the errors propagate into the learned drift and diffusion. We observe that the ambient covariance~$Λ$ already encodes coordinate-invariant tangent-space information, its range spanning the tangent bundle. Using this, we construct a tangent-bundle penalty and an inverse-consistency penalty for a three-stage pipeline (chart learning, latent drift, latent diffusion) that learns a single nonlinear chart and the latent SDE. The penalties induce a function-space metric, the $ρ$-metric, strictly weaker than the Sobolev $H^1$ norm yet achieving the same chart-quality generalization rate up to logarithmic factors. For the drift, we derive an encoder-pullback target via Itô's formula on the learned encoder and prove a bias decomposition showing the standard decoder-side formula carries systematic error for any imperfect chart. Under a $W^{2,\infty}$ chart-convergence assumption, chart-level error propagates controllably to weak convergence of the ambient dynamics and to convergence of radial mean first-passage times. Experiments on four surfaces embedded in up to $201$ ambient dimensions reduce radial MFPT error by $50$--$70\%$ under rotation dynamics and achieve the lowest inter-well MFPT error on most surface--transition pairs under metastable Müller--Brown Langevin dynamics, while reducing end-to-end ambient coefficient errors by up to an order of magnitude relative to an unregularized autoencoder.

Related papers

• Fluid-DiT: Graph-Free Diffusion Transformers for Fluid Flow Simulations Learning [50.053186229257555]
  We propose a Graph-Free Diffusion Transformer that replaces graph message passing with attention-based denoising.<n>By leveraging the transformer's global receptive field, Fluid-DiT naturally captures both local flow structures and long-range correlations.<n>It consistently outperforms graph-based diffusion baselines in both sample quality and distributional accuracy.
  arXiv  Detail & Related papers  (2026-08-07T12:28:45Z)
• Universal Dynamic Scaling of 2D Quantum Ising Transition on the Fuzzy Sphere [1.1082320175055462]
  We revisit the problem of textitreal-time quantum dynamics of the paradigmatic two dimensional transverse-field Ising model.<n>We study the finite-time scaling behavior of the squared order parameter $langle m_z2 rangle$, the excitation energy density $Q$, and the two-point correlation function of $m_z$.
  arXiv  Detail & Related papers  (2026-07-20T14:59:20Z)
• Higher-Order Geometric Updates for Levenberg-Marquardt Method via Riemann Normal Coordinates [1.7812378608633406]
  least-squares optimization is central to regression, physics-informed neural networks, and other machine-learning tasks.<n>RNC-LM improves convergence and robustness in curved valleys and rank-deficient problems.<n>It achieves a 34-fold speedup over standard LM on a large-scale machine-learning potential-energy-surface fitting task.
  arXiv  Detail & Related papers  (2026-07-08T16:39:03Z)
• When to Stop Reusing: Dynamic Gradient Gating for Sample-Efficient RLVR [46.88928401641895]
  Reinforcement Learning with Verifiable Rewards (RLVR) has become the dominant paradigm for advanced reasoning in Large Language Models (LLMs)<n>In RLVR, reuse each rollout batch for multiple gradient updates amplifies policy shift, leading to severe performance degradation.<n>We identify the textitDisproportionate Weight Divergence (DWD) phenomenon: performance degradation is synchronized a sharp surge in the textttlm_head weight change, while intermediate layers remain stable.<n>We propose textitDynamic Gradient Gating (DGG), a lightweight intervention
  arXiv  Detail & Related papers  (2026-05-19T06:23:43Z)
• Universal Spin Squeezing Dynamical Phase Transitions across Lattice Geometries, Dimensions, and Microscopic Couplings [0.0]
  Bogoliubov theory recovers the previously identified scaling $a_Z* propto L$ in the long-range interacting regime $ d+2$.<n>This uncovers a previously unrecognized sub-linear regime for short-range interactions.<n>These findings provide a versatile route toward controlling entanglement generation in Rydberg-array, polar molecule, and trapped-ion platforms.
  arXiv  Detail & Related papers  (2026-05-13T18:00:07Z)
• Minimax Optimality and Spectral Routing for Majority-Vote Ensembles under Markov Dependence [6.908972852063454]
  Majority-vote ensembles achieve variance reduction by averaging over diverse, approximately independent base learners.<n>We provide a minimax characterization of this phenomenon for discrete classification in a fixed-dimensional Markov setting.<n>Experiments on synthetic Markov chains, 2D spatial grids, the 128-dataset UCR archive, and Atari DQN ensembles validate the theoretical predictions.
  arXiv  Detail & Related papers  (2026-04-15T02:32:30Z)
• Adaptive Probability Flow Residual Minimization for High-Dimensional Fokker-Planck Equations [14.22534820071447]
  Solving high-dimensional Fokker-Planck equations is a challenge in computational physics and dynamics.<n>Existing deep learning approaches, such as Physics-Informed Neural Networks, face computational challenges as dimensionality increases.<n>We propose the Adaptive Probability Flow Residual Minimization (A-PFRM) method.
  arXiv  Detail & Related papers  (2025-12-22T09:31:31Z)
• Learning vertical coordinates via automatic differentiation of a dynamical core [39.817742239477255]
  We propose a framework to define a parametric vertical coordinate system as a learnable component within a differentiable dynamical core.<n>We develop an end-to-end differentiable numerical solver for the two-dimensional non-hydrostatic equations on an Arakawa C-grid.<n>We demonstrate that these learned coordinates reduce the mean squared error by a factor of 1.4 to 2 in non-linear statistical benchmarks.
  arXiv  Detail & Related papers  (2025-12-19T18:31:07Z)
• Implicit Augmentation from Distributional Symmetry in Turbulence Super-Resolution [2.4095472682599417]
  We show that standard convolutional neural networks (CNNs) can partially acquire rotational symmetry without explicit augmentation or specialized architectures.<n>Using 3D channel-flow with differing anisotropy, we find that models trained on more isotropic mid-plane data achieve lower equivariance error.<n>These results clarify when rotational symmetry must be explicitly incorporated into learning algorithms and when it can be obtained directly from turbulence.
  arXiv  Detail & Related papers  (2025-09-25T02:31:56Z)
• Decentralized Nonconvex Composite Federated Learning with Gradient Tracking and Momentum [78.27945336558987]
  Decentralized server (DFL) eliminates reliance on client-client architecture.<n>Non-smooth regularization is often incorporated into machine learning tasks.<n>We propose a novel novel DNCFL algorithm to solve these problems.
  arXiv  Detail & Related papers  (2025-04-17T08:32:25Z)
• Point Cloud Denoising With Fine-Granularity Dynamic Graph Convolutional Networks [58.050130177241186]
  Noise perturbations often corrupt 3-D point clouds, hindering downstream tasks such as surface reconstruction, rendering, and further processing. This paper introduces finegranularity dynamic graph convolutional networks called GDGCN, a novel approach to denoising in 3-D point clouds.
  arXiv  Detail & Related papers  (2024-11-21T14:19:32Z)
• On Single Index Models beyond Gaussian Data [45.875461749455994]
  Sparse high-dimensional functions have arisen as a rich framework to study the behavior of gradient-descent methods. In this work, we explore extensions of this picture beyond the Gaussian setting where both stability or symmetry might be violated. Our main results establish that Gradient Descent can efficiently recover the unknown direction $theta*$ in the high-dimensional regime.
  arXiv  Detail & Related papers  (2023-07-28T20:52:22Z)
• 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)
• Dynamical mean-field theory for stochastic gradient descent in Gaussian mixture classification [25.898873960635534]
  We analyze in a closed learning dynamics of gradient descent (SGD) for a single-layer neural network classifying a high-dimensional landscape. We define a prototype process for which can be extended to a continuous-dimensional gradient flow. In the full-batch limit, we recover the standard gradient flow.
  arXiv  Detail & Related papers  (2020-06-10T22:49:41Z)

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.