A convex neural network is trained inside an elastoplastic stress integration loop using force equilibrium losses to identify yield functions from full-field displacement data.
Operator inference for non-intrusive model reduction with quadratic manifolds,
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 6roles
background 1polarities
background 1representative citing papers
FastQM rotates a candidate basis of singular vectors on the Stiefel manifold to maximize quadratic manifold approximation quality, with feature-space cost independent of full dimension, shown on turbulent airfoil-wake data.
Oscillatory state-space models with PDE-aware spectral bases are introduced as inductive biases for PINNs, yielding improved accuracy and lower memory on forward, inverse, and up to 100D PDE tasks.
A dynamic subspace method parameterizes low-dimensional bases as geodesic paths on the Grassmannian to track evolving physics in nonlinear systems, achieving higher accuracy than static approximations at the same rank.
Cut-DeepONet uses a lifting strategy and an auxiliary network to predict discontinuity locations, enabling a neural operator to learn smooth components in partitioned regions and outperforming prior methods on benchmark PDEs with fewer parameters even on low-resolution data.
A novel high-order stabilization-free virtual element method is developed for general second-order elliptic eigenvalue problems, with optimal a priori error estimates for eigenspaces and eigenvalues, validated on various polygonal meshes.
citing papers explorer
-
Physics-Informed Discovery of Yield Functions in Plasticity via Convex Neural Representations
A convex neural network is trained inside an elastoplastic stress integration loop using force equilibrium losses to identify yield functions from full-field displacement data.
-
Fast Quadratic Manifold Learning For Nonlinear Dimensionality Reduction in Large-scale Systems using Riemannian Optimization
FastQM rotates a candidate basis of singular vectors on the Stiefel manifold to maximize quadratic manifold approximation quality, with feature-space cost independent of full dimension, shown on turbulent airfoil-wake data.
-
Oscillatory State-Space Models as Inductive Biases for Physics-Informed Neural PDE Solvers
Oscillatory state-space models with PDE-aware spectral bases are introduced as inductive biases for PINNs, yielding improved accuracy and lower memory on forward, inverse, and up to 100D PDE tasks.
-
A Dynamic Subspace Approach for Low-rank Approximation of Large-scale Nonlinear Systems
A dynamic subspace method parameterizes low-dimensional bases as geodesic paths on the Grassmannian to track evolving physics in nonlinear systems, achieving higher accuracy than static approximations at the same rank.
-
Smooth Piecewise Cutting for Neural Operator to Handle Discontinuities and Sharp Transitions
Cut-DeepONet uses a lifting strategy and an auxiliary network to predict discontinuity locations, enabling a neural operator to learn smooth components in partitioned regions and outperforming prior methods on benchmark PDEs with fewer parameters even on low-resolution data.
-
A high order stabilization-free virtual element method for general second-order elliptic eigenvalue problem
A novel high-order stabilization-free virtual element method is developed for general second-order elliptic eigenvalue problems, with optimal a priori error estimates for eigenspaces and eigenvalues, validated on various polygonal meshes.