NLPOpt-Net is an unsupervised neural architecture that learns parametric solutions to constrained NLPs by pairing a backbone network with quadratic projection layers that guarantee feasibility and near-zero constraint violations.
When and why pinns fail to train: A neural tangent kernel perspective,
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
SOLIS recovers interpretable physical parameters for nonlinear systems by learning state-conditioned Quasi-LPV neural surrogates without assuming a fixed global equation.
A DFL-TFC framework with orthogonal polynomial expansion and domain mapping solves the governing DE for bending of exponentially loaded tapered perforated beams more efficiently than PINNs.
citing papers explorer
-
NLPOpt-Net: A Learning Method for Nonlinear Optimization with Feasibility Guarantees
NLPOpt-Net is an unsupervised neural architecture that learns parametric solutions to constrained NLPs by pairing a backbone network with quadratic projection layers that guarantee feasibility and near-zero constraint violations.
-
SOLIS: Physics-Informed Learning of Interpretable Neural Surrogates for Nonlinear Systems
SOLIS recovers interpretable physical parameters for nonlinear systems by learning state-conditioned Quasi-LPV neural surrogates without assuming a fixed global equation.
-
Physics-Informed Functional Link Constrained Framework with Domain Mapping for Solving Bending Analysis of an Exponentially Loaded Perforated Beam
A DFL-TFC framework with orthogonal polynomial expansion and domain mapping solves the governing DE for bending of exponentially loaded tapered perforated beams more efficiently than PINNs.