In a 1D plasma benchmark, classical conservative finite volume structure achieves rollout MSE of 7.35e-9 and wins 60/64 cases, outperforming neural baselines focused on one-step accuracy.
An adaptive augmented lagrangian method for training physics and equality constrained artificial neural networks.arXiv preprint arXiv:2306.04904, 2023
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Lagrange multipliers in constrained MLE and LS converge asymptotically to zero under correct specification, justifying zero initialization in algorithms like augmented Lagrangian methods.
citing papers explorer
-
Conservative Discrete Structure Stabilizes Autoregressive Rollouts in a 1D Drift Diffusion Poisson Benchmark
In a 1D plasma benchmark, classical conservative finite volume structure achieves rollout MSE of 7.35e-9 and wins 60/64 cases, outperforming neural baselines focused on one-step accuracy.
-
Lagrange multipliers in Maximum likelihood estimations and Least squares problems with Constraints
Lagrange multipliers in constrained MLE and LS converge asymptotically to zero under correct specification, justifying zero initialization in algorithms like augmented Lagrangian methods.