Local LMO is a new projection-free method that achieves the convergence rates of projected gradient descent for constrained optimization by using local linear minimization oracles over small balls.
Pinet: Optimizing hard- constrained neural networks with orthogonal projection layers
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
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.
SnareNet introduces a repair layer that navigates the range space of constraints plus adaptive relaxation training to enforce hard non-convex constraints on neural network outputs more reliably than prior methods.
Flow Gym supplies a JAX-based framework with standardized interfaces, modular components, and utilities to develop, benchmark, train, and deploy flow-field quantification methods such as PIV on both synthetic and experimental data.
A hybrid primal-dual optimization proxy solver certifies optimality gaps via duality and achieves over 1000x speedup with a guaranteed maximum 2% gap on large-scale transmission systems.
A convex-minimization controller for affine inequalities is approximated by neural networks that act as universal formulas independent of state dimension for bounded input and constraint sizes.
AdamFLIP treats PDE constraint residuals in PINNs as a controlled dynamical system, computes Lagrange multipliers via feedback linearization to drive residuals to zero, and applies Adam-style adaptation to the resulting gradient for scalable hard-constrained training.
SynthPix streams synthetic PIV image pairs directly into training or benchmarking loops using JAX parallelism and a configuration interface matched to real imaging parameters.
citing papers explorer
-
Local LMO: Constrained Gradient Optimization via a Local Linear Minimization Oracle
Local LMO is a new projection-free method that achieves the convergence rates of projected gradient descent for constrained optimization by using local linear minimization oracles over small balls.
-
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.
-
SnareNet: Flexible Repair Layers for Neural Networks with Hard Constraints
SnareNet introduces a repair layer that navigates the range space of constraints plus adaptive relaxation training to enforce hard non-convex constraints on neural network outputs more reliably than prior methods.
-
Flow Gym: A framework for the development, benchmarking, training, and deployment of flow-field quantification methods
Flow Gym supplies a JAX-based framework with standardized interfaces, modular components, and utilities to develop, benchmark, train, and deploy flow-field quantification methods such as PIV on both synthetic and experimental data.
-
Self-Certifying Primal-Dual Optimization Proxies for Large-Scale Batch Economic Dispatch
A hybrid primal-dual optimization proxy solver certifies optimality gaps via duality and achieves over 1000x speedup with a guaranteed maximum 2% gap on large-scale transmission systems.
-
Universal Formulas for Safe Control and Their Neural Network Approximations
A convex-minimization controller for affine inequalities is approximated by neural networks that act as universal formulas independent of state dimension for bounded input and constraint sizes.
-
AdamFLIP: Adaptive Momentum Feedback Linearization Optimization for Hard Constrained PINN Training
AdamFLIP treats PDE constraint residuals in PINNs as a controlled dynamical system, computes Lagrange multipliers via feedback linearization to drive residuals to zero, and applies Adam-style adaptation to the resulting gradient for scalable hard-constrained training.
-
SynthPix: A lightspeed PIV image generator
SynthPix streams synthetic PIV image pairs directly into training or benchmarking loops using JAX parallelism and a configuration interface matched to real imaging parameters.
- HardNet++: Nonlinear Constraint Enforcement in Neural Networks