4 papers
Frequency Matters: Fast Model-Agnostic Data Curation for Pruning and Quantization
Francesco Pio Monaco, Elia Cunegatti, Flavio Vella +1
Post-training model compression is essential for enhancing the portability of Large Language Models (LLMs) while preserving their performance. While several compression approaches…
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…
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…
Physics-constrained DeepONet for Surrogate CFD models: a curved backward-facing step case
Anas Jnini, Harshinee Goordoyal, Sujal Dave +3
The Physics-Constrained DeepONet (PC-DeepONet), an architecture that incorporates fundamental physics knowledge into the data-driven DeepONet model, is presented in this study. Thi…