physics-informed neural networks
Physics-informed neural networks are machine learning models that incorporate physical laws and constraints as part of the training process, ensuring that predictions remain consistent with known physical behaviors.
- A Regularized Newton Method for Nonconvex Optimization with Global and Local Complexity Guarantees
- Consistency of Physics-Informed Neural Networks for Second-Order Elliptic Equations
- Equivariant Eikonal Neural Networks: Grid-Free, Scalable Travel-Time Prediction on Homogeneous Spaces
- FP64 is All You Need: Rethinking Failure Modes in Physics-Informed Neural Networks
- Gradient Alignment in Physics-informed Neural Networks: A Second-Order Optimization Perspective
- HyPINO: Multi-Physics Neural Operators via HyperPINNs and the Method of Manufactured Solutions
- Hybrid Boundary Physics-Informed Neural Networks for Solving Navier-Stokes Equations with Complex Boundary
- Improving Energy Natural Gradient Descent through Woodbury, Momentum, and Randomization
- Integration Matters for Learning PDEs with Backwards SDEs
- Mitigating Instability in High Residual Adaptive Sampling for PINNs via Langevin Dynamics
- Neuro-Spectral Architectures for Causal Physics-Informed Networks
- Nyström-Accelerated Primal LS-SVMs: Breaking the $O(an^3)$ Complexity Bottleneck for Scalable ODEs Learning
- PALQO: Physics-informed model for Accelerating Large-scale Quantum Optimization
- PINN Balls: Scaling Second-Order Methods for PINNs with Domain Decomposition and Adaptive Sampling
- PINNs with Learnable Quadrature
- Physics-informed machine learning with domain decomposition and global dynamics for three-dimensional intersecting flows
- Uncertainty Quantification for Physics-Informed Neural Networks with Extended Fiducial Inference