Research
Poisson-GENERIC Neural Operators: Exact Metriplectic Structure in Function Space via Casimir Entropies
arXiv:2610.05570v1 Announce Type: new Abstract: Existing thermodynamically consistent neural operators impose the GENERIC degeneracy conditions by projecting the reversible operator onto the complemen
arXiv:2610.05570v1 Announce Type: new Abstract: Existing thermodynamically consistent neural operators impose the GENERIC degeneracy conditions by projecting the reversible operator onto the complement of the entropy gradient. This makes the operator state-dependent and forfeits the Jacobi identity, so the result is metriplectic-degenerate rather than metriplectic. We instead obtain degeneracy the way GENERIC does. For nonlinear transport, the reversible operator L is the compatible Lie-Poisson pencil alpha D+lambda(uD+Du); otherwise it is a constant, trivially Poisson Fourier multiplier. On an augmented state (u,s) with a latent entropy density, S=int s is a Casimir of L, so L,elta S/elta z=0 holds identically without projection. The energy combines a fixed mechanical quadratic, a learned gauge-free potential, and a convex internal energy. The friction operator M=AA^op satisfies M,elta E/elta z=0 pointwise, and its Onsager parity structure permits diffusion and damping while provably excluding transport. For any parameters, skewness, positivity, both degeneracies, and the Jacobi identity (on the resolved band for the Lie-Poisson term) hold to machine precision. Heat conduction and damped waves admit exact closed-form friction operators, the second law bounds physical energy under a checkable curvature condition, and a discrete-gradient integrator yields exact discrete first and second laws. On four PDEs in 1D and 2D with three backbones (FNO, Transolver, CNO), the model wins 61 of 72 seed-level comparisons against same-backbone unconstrained baselines, learns the exact transport and wave symbols, matches the true dissipation rate within 13% on heat and Burgers, and dissipates nothing on advection. A constant-L ablation isolates the cost of exact Jacobi as the loss of Burgers, while a learned-entropy ablation injects energy on every reversible-irreversible problem.
Related
- A Constitutive Markov Physics-Informed Neural Operator (MPNO) for Autoregressive Stability in Transient Dynamics
- WINO: A Weak-Form Physics Informed Neural Operator for Hyperelasticity on Variable Domains
- Vector-Valued Reproducing Kernel Banach Spaces for Neural Networks and Operators
- Certified and accurate computation of function space norms of deep neural networks
- Learning Operators by Regularized Stochastic Gradient Descent with Operator-valued Kernels
Source: arXiv cs.LG | 2026-10-06