stat.MLNov 15, 2026

Learning Autoregressive Neural Operators on Solver-Defined Physical Constraint Manifolds

Authors: Nannan Zhou, Guanmeng Xian, Ning Yang

Organizations: School of Computer Science, Sichuan University, Chengdu, China · National Key Laboratory of Fundamental Algorithms and Models for Engineering Numerical Simulation, Chengdu, China

Abstract

Autoregressive neural operators approximate time-dependent PDE solvers by repeatedly composing a learned transition, although the resulting states need not remain feasible under the discrete constraints of the numerical problem. We study this issue for incompressible flow, where each velocity state must satisfy solver-level incompressibility together with prescribed boundary values. We formulate autoregressive operator learning as a map between solver-defined affine feasible sets and introduce PCM-NO, a projected-residual realization of this feasible-transition principle. The neural backbone predicts a candidate state increment, a fixed tangent projection extracts its admissible component, and a metric retraction maps the advanced state to the prescribed feasible set. With exact affine constraint solves, the resulting transition is closed on the feasible set, while an affine identity separates admissible-update parameterization from state-level closure. With approximate solves, tangent-only residuals admit a cumulative upper bound, whereas per-step retraction resets feasibility to the residual achieved by the current solve. Experiments on periodic Navier--Stokes flow and lid-driven cavity flow demonstrate the superiority of PCM-NO in preserving solver-level constraints over long autoregressive rollouts and under parameter, boundary-value, and resolution shifts, while achieving lower rollout errors and better flow-specific diagnostics across both in-distribution and stress settings.

Figures & tables

Appendix figures & tables5 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

May 25, 2026

Autoregression-Free Neural Operators for Time-Dependent PDEs

Neural operators learn mappings from function-dependent inputs to solutions, providing an effective framework for solving partial differential equations (PDEs). For time-dependent PDEs, existing methods typically perform long-horizon prediction through autoregressive rollout directly in high-dimensional physical field spaces, where each predicted state is recursively fed back as the input for the next step. Although effective for short-term prediction, this autoregressive rollout and the lack of continuous-time modeling lead to progressive error accumulation over long-horizon rollouts. In this work, we propose Autoregression-Free Neural Operators (AFNO), which map the time evolution of PDEs into a latent space and model continuous-time vector fields within it. AFNO uses flow matching to learn the latent vector field, thereby enabling continuous evolution over extended horizons, avoiding autoregressive rollout and capturing dynamics under varying parameter configurations through explicit conditioning on physical parameters. Theoretical analysis and extensive experiments on six PDEs demonstrate that AFNO improves long-horizon prediction stability and consistently reduces rollout errors compared with the baselines.
Nov 24, 2025

A physics-constrained neural solver for incompressible flows without labeled data

We present a physics-constrained neural solver for incompressible flow that requires neither labeled data nor supervised pretraining. The solver enforces incompressibility and boundary conditions (BCs) to strict tolerances. We attribute the limited Reynolds numbers of existing physics-informed approaches to insufficient enforcement of these constraints, on which conventional finite-difference and finite-volume solvers depend. We therefore formulate incompressible flow as a constrained optimization problem within the physics- and equality-constrained artificial neural network (PECANN) framework: the pressure Poisson residual is minimized subject to the momentum equations, continuity equation, and BCs imposed as equality constraints on the primitive variables, while a conditionally adaptive augmented Lagrangian method enforces each constraint. The pressure Poisson objective proves critical. Across all benchmarks, replacing it with the momentum residual fails to converge to accurate solutions under identical architecture and constraint enforcement, which we attribute to the global elliptic coupling of pressure and velocity that local momentum-residual minimization lacks. For advection-dominated flows, we introduce an adaptive vanishing entropy viscosity that stabilizes training while leaving the converged solution unchanged. The solver predicts lid-driven cavity flow up to Re = 7,500 with centerline velocity profiles matching benchmark data, and is further validated on flow over a backward-facing step at Re = 800, 3D unsteady Beltrami flow, and steady and unsteady flow past a circular cylinder under an inflow-outflow configuration, for which an ablation study identifies admissible outlet BCs for velocity and pressure. From a randomly initialized network and without external perturbations, the solver captures the spontaneous onset of periodic vortex shedding in unsteady cylinder flow.
Nov 2, 2026

DynaSolver: A Neural Operator for Autoregressive 4D Flow Prediction with Dynamic Boundaries

Neural operators provide efficient surrogates for computational fluid dynamics (CFD), but most are designed for static geometries and are not equipped to model unsteady flows induced by continuously moving boundaries. We study dynamic-boundary 4D CFD prediction for articulated moving geometries and introduce RoboCFD-4D, a temporally resolved robotic CFD benchmark spanning diverse morphologies and flow conditions. To address the computational and autoregressive challenges of this setting, we propose DynaSolver, a neural operator that explicitly conditions on boundary evolution and causal flow history. DynaSolver employs an efficient physical-token formulation that amortizes point-to-token projection across the operator stack, substantially reducing repeated point-space spatio-temporal computation while retaining accurate point-level reconstruction. We further introduce Replay-Augmented Parallel Training, which exposes the model to autoregressively generated histories while preserving parallel dense supervision, narrowing the gap between ground-truth-conditioned training and autoregressive rollout. Experiments on RoboCFD-4D show that DynaSolver achieves the best full-rollout accuracy among a broad range of learned CFD surrogates, with its advantage increasing as rollout proceeds, indicating substantially reduced autoregressive error accumulation. Project page: https://made-gpt.github.io/DynaSolver-ProjectPage.