A velocity-weighted L2 loss for PINNs on the BGK model guarantees convergence to the physical solution by penalizing high-velocity errors.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.LG 2verdicts
UNVERDICTED 2roles
method 1polarities
use method 1representative citing papers
CR-Net uses cross-layer low-rank residuals in a dual-path network plus specialized recomputation to outperform prior low-rank methods on 60M-7B model pre-training while using less compute and memory.
citing papers explorer
-
A Theory-guided Weighted $L^2$ Loss for solving the BGK model via Physics-informed neural networks
A velocity-weighted L2 loss for PINNs on the BGK model guarantees convergence to the physical solution by penalizing high-velocity errors.
-
CR-Net: Scaling Parameter-Efficient Training with Cross-Layer Low-Rank Structure
CR-Net uses cross-layer low-rank residuals in a dual-path network plus specialized recomputation to outperform prior low-rank methods on 60M-7B model pre-training while using less compute and memory.