Structure-Aware Epistemic Uncertainty Quantification for Neural Operator PDE Surrogates

• URL: http://arxiv.org/abs/2603.11052v1
• Date: Tue, 24 Feb 2026 10:17:24 GMT
• Title: Structure-Aware Epistemic Uncertainty Quantification for Neural Operator PDE Surrogates
• Abstract summary: Uncertainty quantification (UQ) must be both computationally efficient and spatially faithful.<n>We propose a structure-aware UQ scheme that exploits the modular anatomy common to modern NOs.<n> Experiments on challenging PDE benchmarks demonstrate that the proposed structure-aware design yields more reliable coverage, tighter bands, and improved residual-uncertainty alignment.
• Score: 10.39662017167378
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Neural operators (NOs) provide fast, resolution-invariant surrogates for mapping input fields to PDE solution fields, but their predictions can exhibit significant epistemic uncertainty due to finite data, imperfect optimization, and distribution shift. For practical deployment in scientific computing, uncertainty quantification (UQ) must be both computationally efficient and spatially faithful, i.e., uncertainty bands should align with the localized residual structures that matter for downstream risk management. We propose a structure-aware epistemic UQ scheme that exploits the modular anatomy common to modern NOs (lifting-propagation-recovering). Instead of applying unstructured weight perturbations (e.g., naive dropout) across the entire network, we restrict Monte Carlo sampling to a module-aligned subspace by injecting stochasticity only into the lifting module, and treat the learned solver dynamics (propagation and recovery) as deterministic. We instantiate this principle with two lightweight lifting-level perturbations, including channel-wise multiplicative feature dropout and a Gaussian feature perturbation with matched variance, followed by standard calibration to construct uncertainty bands. Experiments on challenging PDE benchmarks (including discontinuous-coefficient Darcy flow and geometry-shifted 3D car CFD surrogates) demonstrate that the proposed structure-aware design yields more reliable coverage, tighter bands, and improved residual-uncertainty alignment compared with common baselines, while remaining practical in runtime.

Related papers

• Randomized neural operator for parametric PDEs with fast training and conformal uncertainty quantification [47.720075875232226]
  We introduce PCA--RaNN, a neural operator that combines a PCA-based dimensionality reduction with fixed random features.<n>It recasts operator learning as fixed regression, reducing latent regression to three orders of magnitude.
  arXiv  Detail & Related papers  (2026-06-28T15:02:26Z)
• Structure-Preserving Neural Surrogates with Tractable Uncertainty Quantification [5.8001568807112855]
  Recent advances in machine learning provide a means of near-real-time solution to partial differential equations (PDEs)<n>We construct data-driven reduced-order models that serve as structure-preserving, real-time surrogates.
  arXiv  Detail & Related papers  (2026-06-10T04:27:23Z)
• Diffusion-Based Stochastic Operator Networks for Uncertainty Quantification in Stochastic Partial Differential Equations [0.3290514527479967]
  We introduce a novel framework for uncertainty quantification of solution operators associated with partial differential equations (SPDEs)<n>The proposed method, namely the Operator Network (SON), is constructed by combining the structure of the Deep Operator Network (DeepONet) with Neural Networks (SNNs)<n> Numerical experiments on benchmark SPDEs under multiple uncertainty sources demonstrate the accuracy and robustness of the proposed method.
  arXiv  Detail & Related papers  (2026-05-16T18:19:45Z)
• Decision-Focused Federated Learning Under Heterogeneous Objectives and Constraints [45.88028371034407]
  We build on the well-known SPO+ approach and develop heterogeneity bounds for the SPO+ surrogate loss.<n>In the case of strongly convex feasible regions, sharper bounds are derived due to the stability.<n>We implement a FedAvg-style DFFL set of experiments on both polyhedral and strongly convex problems.
  arXiv  Detail & Related papers  (2026-04-21T22:22:39Z)
• Uncertainty Quantification in PINNs for Turbulent Flows: Bayesian Inference and Repulsive Ensembles [3.758814046658822]
  Physics-informed neural networks (PINNs) have emerged as a promising framework for solving inverse problems governed by partial differential equations (PDEs)<n>We develop and evaluate a set of probabilistic extensions of PINNs for uncertainty quantification in turbulence modeling.<n>The proposed framework combines (i) Bayesian PINNs with Hamiltonian Monte Carlo sampling and a tempered multi-component likelihood, (ii) Monte Carlo dropout, and (iii) repulsive deep ensembles that enforce diversity in function space.
  arXiv  Detail & Related papers  (2026-04-18T22:02:54Z)
• Equivariant Evidential Deep Learning for Interatomic Potentials [55.6997213490859]
  Uncertainty quantification is critical for assessing the reliability of machine learning interatomic potentials in molecular dynamics simulations.<n>Existing UQ approaches for MLIPs are often limited by high computational cost or suboptimal performance.<n>We propose textitEquivariant Evidential Deep Learning for Interatomic Potentials ($texte2$IP), a backbone-agnostic framework that models atomic forces and their uncertainty jointly.
  arXiv  Detail & Related papers  (2026-02-11T02:00:25Z)
• Generalizing GNNs with Tokenized Mixture of Experts [75.8310720413187]
  We show that improving stability requires reducing reliance on shift-sensitive features, leaving an irreducible worst-case generalization floor.<n>We propose STEM-GNN, a pretrain-then-finetune framework with a mixture-of-experts encoder for diverse computation paths.<n>Across nine node, link, and graph benchmarks, STEM-GNN achieves a stronger three-way balance, improving robustness to degree/homophily shifts and to feature/edge corruptions while remaining competitive on clean graphs.
  arXiv  Detail & Related papers  (2026-02-09T22:48:30Z)
• Generative Neural Operators through Diffusion Last Layer [13.076028397183897]
  We introduce a lightweight probabilistic head that can be attached to arbitrary neural operator backbones to model predictive uncertainty.<n>Motivated by the relative smoothness and low-dimensional structure often exhibited by PDE solution distributions, we parameterize the conditional output distribution directly in function space.<n>Across PDE operator learning benchmarks, prediction improves and uncertainty-aware.
  arXiv  Detail & Related papers  (2026-02-04T02:10:53Z)
• Analyzing and Improving Diffusion Models for Time-Series Data Imputation: A Proximal Recursion Perspective [45.713195454899875]
  Diffusion models (DMs) have shown promise for Time-Series Data Imputation.<n>DMs' performance remains inconsistent in complex scenarios.<n>We propose a novel framework called SPIRIT (Semi-Proximal Transport Regularized time-series Imputation)
  arXiv  Detail & Related papers  (2026-02-01T12:11:57Z)
• Variationally correct operator learning: Reduced basis neural operator with a posteriori error estimation [3.8135482236014133]
  Minimizing PDE-residual losses is a common strategy to promote physical consistency in neural operators.<n>This work develops a variationally correct operator learning framework by constructing first-order system least-squares (FOSLS) objectives.<n>We provide a rigorous convergence analysis that bounds the total error by the sum of finite element discretization bias, reduced basis truncation error, neural network approximation error, and statistical estimation errors.
  arXiv  Detail & Related papers  (2025-12-24T18:37:59Z)
• The Procrustean Bed of Time Series: The Optimization Bias of Point-wise Loss [53.542743390809356]
  This paper aims to provide a first-principles analysis of the Expectation of Optimization Bias (EOB)<n>Our analysis reveals a fundamental paradigm paradox: the more deterministic and structured the time series, the more severe the bias by point-wise loss function.<n>We present a concrete solution that simultaneously achieves both principles via DFT or DWT.
  arXiv  Detail & Related papers  (2025-12-21T06:08:22Z)
• Optimal Regularization Under Uncertainty: Distributional Robustness and Convexity Constraints [9.77322868877488]
  We introduce a framework for distributionally robust optimal regularization.<n>We show how the resulting robust regularizers interpolate between computation of the training distribution and uniform priors.
  arXiv  Detail & Related papers  (2025-10-03T19:35:38Z)
• Deep set based operator learning with uncertainty quantification [14.436821529642893]
  We propose UQ-SONet, a permutation-invariant operator learning framework with built-in uncertainty quantification (UQ)<n>Our model integrates a set transformer embedding to handle sparse and variable sensor locations, and employs a conditional variational autoencoder (cVAE) to approximate the conditional distribution of the solution operator.
  arXiv  Detail & Related papers  (2025-09-30T01:36:18Z)
• A Conformal Prediction Framework for Uncertainty Quantification in Physics-Informed Neural Networks [0.9613011825024471]
  PINNs have emerged as a powerful framework for solving PDEs.<n>Existing uncertainty quantification approaches for PINNs generally lack rigorous statistical guarantees.<n>We introduce a distribution-free conformal prediction framework for UQ in PINNs.
  arXiv  Detail & Related papers  (2025-09-17T06:12:48Z)
• Adaptive Dual Uncertainty Optimization: Boosting Monocular 3D Object Detection under Test-Time Shifts [80.32933059529135]
  Test-Time Adaptation (TTA) methods have emerged to adapt to target distributions during inference.<n>We propose Dual Uncertainty Optimization (DUO), the first TTA framework designed to jointly minimize both uncertainties for robust M3OD.<n>In parallel, we design a semantic-aware normal field constraint that preserves geometric coherence in regions with clear semantic cues.
  arXiv  Detail & Related papers  (2025-08-28T07:09:21Z)
• Rao-Blackwell Gradient Estimators for Equivariant Denoising Diffusion [55.95767828747407]
  In domains such as molecular and protein generation, physical systems exhibit inherent symmetries that are critical to model.<n>We present a framework that reduces training variance and provides a provably lower-variance gradient estimator.<n>We also present a practical implementation of this estimator incorporating the loss and sampling procedure through a method we call Orbit Diffusion.
  arXiv  Detail & Related papers  (2025-02-14T03:26:57Z)
• Which Invariance Should We Transfer? A Causal Minimax Learning Approach [18.71316951734806]
  We present a comprehensive minimax analysis from a causal perspective. We propose an efficient algorithm to search for the subset with minimal worst-case risk. The effectiveness and efficiency of our methods are demonstrated on synthetic data and the diagnosis of Alzheimer's disease.
  arXiv  Detail & Related papers  (2021-07-05T09:07:29Z)

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.