activity
20242026
most citedGauss-Newton Natural Gradient Descent for Physics-Informed Computational Fluid Dynamics

2 citations · 3 across the 7 of their papers we have counts for

collaborators
Showing cs.LGShow all

2 papers · 1 filter

cs.LG2025

Dual Natural Gradient Descent for Scalable Training of Physics-Informed Neural Networks

Anas Jnini, Flavio Vella

Natural-gradient methods markedly accelerate the training of Physics-Informed Neural Networks (PINNs), yet their Gauss--Newton update must be solved in the parameter space, incurri…

cs.LG2025

Riemann Tensor Neural Networks: Learning Conservative Systems with Physics-Constrained Networks

Anas Jnini, Lorenzo Breschi, Flavio Vella

Divergence-free symmetric tensors (DFSTs) are fundamental in continuum mechanics, encoding conservation laws such as mass and momentum conservation. We introduce Riemann Tensor Neu…