Factorized Neural Operators Decompose Dynamic and Persistent Responses

• URL: http://arxiv.org/abs/2606.16900v1
• Date: Mon, 15 Jun 2026 16:09:04 GMT
• Title: Factorized Neural Operators Decompose Dynamic and Persistent Responses
• Abstract summary: We introduce the Unified Green's Function Framework across domains and propose the Factorized Neural Operators (FaNO)<n>FaNO decomposes spectral representations into equivariant dynamic responses and invariant persistent responses.<n>Mechanistically, we show that the two operator branches spontaneously specialize into distinct physical roles that remain consistent across scales and domains.
• Score: 12.145565874192933
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Physical systems often exhibit heterogeneous mechanisms, where rapidly evolving dynamics coexist with persistent structures. Capturing such multiscale physical behavior remains challenging for existing neural operators, which typically rely on single dominant inductive bias and therefore couple distinct physical responses into a shared representation. We introduce the Unified Green's Function Framework across domains and propose the Factorized Neural Operators (FaNO), which decompose spectral representations into equivariant dynamic responses and invariant persistent responses, leading to better interpretability and generalization. Mechanistically, we show that the two operator branches spontaneously specialize into distinct physical roles that remain consistent across scales and domains: the equivariant branch captures rapidly varying transient dynamics, whereas the invariant branch extracts coherent persistent structures. This factorized mechanism of FaNO improves prediction accuracy, parameter efficiency and cross-scale generalization across physical systems and domains. In particular, it maintains consistent predictions under long-horizon autoregressive rollout, cross-resolution extrapolation and physical-regime shifts. These findings suggest that scalable physical modeling may benefit from moving beyond single-inductive-bias formulations toward factorized operator representations that better reflect the heterogeneous organization of physical systems, accelerating the reliable deployment of machine learning for scientific computing and discovery.

Related papers

• Stable by Construction: Variational Latent Markov Operators for Long-Horizon PDE Prediction [12.736876538921626]
  We introduce latent Markov dynamics in which physical states are represented by latent distributions and evolved through probabilistic transitions.<n>We instantiate the framework as the Variational Autoencoding Markov Operator (VAMO), which combines spatially resolved latent fields, structured Gaussian perturbations, and a neural-operator transition.
  arXiv  Detail & Related papers  (2026-09-15T04:28:59Z)
• Structured Neural Chaos: An Adaptive Surrogate Modeling Framework for Functional Uncertainty Quantification and Global Sensitivity Analysis [3.4686904619645866]
  We introduce the Structured Neural Chaos (sNC) expansion as a surrogate modeling framework for variance-based global sensitivity analysis.<n>The proposed framework retains the interpretability of structured decompositions while leveraging the power of neural networks.
  arXiv  Detail & Related papers  (2026-07-31T00:03:07Z)
• OMNIFLOW: A Physics-Grounded Multimodal Agent for Generalized Scientific Reasoning [51.33849811496781]
  Large Language Models (LLMs) have demonstrated exceptional logical reasoning capabilities but frequently struggle with the continuous dynamics by Partial Differential Equations (PDEs)<n>We propose OMNIFLOW, a multimodal-symbolic architecture designed to ground frozen LLMs in fundamental physical laws without requiring domain-specific parameter updates.<n>We evaluate it on a benchmark spanning microscopic turbulence, theoretical Navier-Stokes, and macroscopic global weather forecasting.
  arXiv  Detail & Related papers  (2026-03-16T18:29:01Z)
• Schrodinger AI: A Unified Spectral-Dynamical Framework for Classification, Reasoning, and Operator-Based Generalization [1.2691047660244335]
  We introduce textbfSchrdinger AI, a unified machine learning framework inspired by quantum mechanics.<n>The system is defined by three tightly coupled components: (1) a time-independent wave-energy solver that treats perception and classification as spectral decomposition under a learned Hamiltonian; (2) a time-dependent dynamical solver governing the evolution of semantic wavefunctions over time, enabling context-aware decision revision, re-routing, and reasoning under environmental changes; and (3) a low-rank operator calculus that learns symbolic transformations such as modular arithmetic through learned quantum-like transition operators
  arXiv  Detail & Related papers  (2025-12-28T04:33:18Z)
• Variational Physics-Informed Ansatz for Reconstructing Hidden Interaction Networks from Steady States [0.0]
  We propose a Variational Physics-Informed Ansatz (VPIA) that infers general interaction operators directly from heterogeneous steady-state data.<n>VPIA embeds the steady-state constraints of the dynamics into a differentiable variational representation.<n>It reconstructs the underlying couplings by minimizing a physics-derived steady-state residual.
  arXiv  Detail & Related papers  (2025-12-06T08:16:32Z)
• Sparse Autoencoder Neural Operators: Model Recovery in Function Spaces [75.45093712182624]
  We introduce a framework that extends sparse autoencoders (SAEs) to lifted spaces and infinite-dimensional function spaces, enabling mechanistic interpretability of large neural operators (NO)<n>We compare the inference and training dynamics of SAEs, lifted-SAE, and SAE neural operators.<n>We highlight how lifting and operator modules introduce beneficial inductive biases, enabling faster recovery, improved recovery of smooth concepts, and robust inference across varying resolutions, a property unique to neural operators.
  arXiv  Detail & Related papers  (2025-09-03T21:57:03Z)
• A Free Probabilistic Framework for Analyzing the Transformer-based Language Models [19.78896931593813]
  We present a formal operator-theoretic framework for analyzing Transformer-based language models using free probability theory.<n>This work offers a principled, though theoretical, perspective on structural dynamics in large language models.
  arXiv  Detail & Related papers  (2025-06-19T19:13:02Z)
• Disentangled Representation Learning for Parametric Partial Differential Equations [31.240283037552427]
  We propose a new paradigm for learning disentangled representations from neural operator parameters. DisentangO is a novel hyper-neural operator architecture designed to unveil and disentangle the latent physical factors of variation embedded within the black-box neural operator parameters. We show that DisentangO effectively extracts meaningful and interpretable latent features, bridging the divide between predictive performance and physical understanding in neural operator frameworks.
  arXiv  Detail & Related papers  (2024-10-03T01:40:39Z)
• SEGNO: Generalizing Equivariant Graph Neural Networks with Physical Inductive Biases [66.61789780666727]
  We show how the second-order continuity can be incorporated into GNNs while maintaining the equivariant property. We also offer theoretical insights into SEGNO, highlighting that it can learn a unique trajectory between adjacent states. Our model yields a significant improvement over the state-of-the-art baselines.
  arXiv  Detail & Related papers  (2023-08-25T07:15:58Z)
• Physics-inspired Equivariant Descriptors of Non-bonded Interactions [0.0]
  We present an extension of the long distance equivariant (LODE) framework that can handle diverse LR interactions in a consistent way. We provide a direct physical interpretation of these using the multipole expansion which allows for simpler and more efficient implementations.
  arXiv  Detail & Related papers  (2023-08-25T07:04:16Z)
• Equivariant Graph Mechanics Networks with Constraints [83.38709956935095]
  We propose Graph Mechanics Network (GMN) which is efficient, equivariant and constraint-aware. GMN represents, by generalized coordinates, the forward kinematics information (positions and velocities) of a structural object. Extensive experiments support the advantages of GMN compared to the state-of-the-art GNNs in terms of prediction accuracy, constraint satisfaction and data efficiency.
  arXiv  Detail & Related papers  (2022-03-12T14:22:14Z)
• Discovering Latent Causal Variables via Mechanism Sparsity: A New Principle for Nonlinear ICA [81.4991350761909]
  Independent component analysis (ICA) refers to an ensemble of methods which formalize this goal and provide estimation procedure for practical application. We show that the latent variables can be recovered up to a permutation if one regularizes the latent mechanisms to be sparse.
  arXiv  Detail & Related papers  (2021-07-21T14:22:14Z)
• Euclideanizing Flows: Diffeomorphic Reduction for Learning Stable Dynamical Systems [74.80320120264459]
  We present an approach to learn such motions from a limited number of human demonstrations. The complex motions are encoded as rollouts of a stable dynamical system. The efficacy of this approach is demonstrated through validation on an established benchmark as well demonstrations collected on a real-world robotic system.
  arXiv  Detail & Related papers  (2020-05-27T03:51:57Z)

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.