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.
DC3: A learn- ing method for optimization with hard constraints
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
verdicts
UNVERDICTED 8representative citing papers
TCR calibrates trust in constraint models via measurement-driven localization and shrinkage to deliver near-oracle feasibility on true networks under localized misspecification.
Expected regret equals covariance between costs and optimal decisions for linear and quadratic stochastic programs, with explicit bounds on the residual.
A Bayesian method embeds linear equality constraints into variational inference for neural networks, yielding reduced credible intervals and fewer constraint violations on a single-particle battery model versus standard variational Bayesian neural networks.
RAYEN enforces hard convex constraints (linear, quadratic, SOC, LMI) on neural networks with negligible overhead while guaranteeing satisfaction at all times.
Probabilistic neural network framework embeds linear equality constraints for dynamic chemical process modeling, showing improved accuracy, calibration, and constraint adherence on reduced data plus faster training on large data.
BIPC framework identifies backdoors in parametric MIPs, trains ML models to predict backdoor values or intervals, and solves constrained reduced problems for faster solutions with limited quality loss.
GraphOPF applies graph learning with physics-informed self-supervision to solve AC-OPF up to 66 times faster than baselines on large systems including the Korean grid while claiming over 99% feasibility.
citing papers explorer
-
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.
-
Trust-Calibrated Certified Repair for Physics-Constrained Decisions under Localized Model Misspecification
TCR calibrates trust in constraint models via measurement-driven localization and shrinkage to deliver near-oracle feasibility on true networks under localized misspecification.
-
Regret Equals Covariance: A Closed-Form Characterization for Stochastic Optimization
Expected regret equals covariance between costs and optimal decisions for linear and quadratic stochastic programs, with explicit bounds on the residual.
-
Learning with Embedded Linear Equality Constraints via Variational Bayesian Inference
A Bayesian method embeds linear equality constraints into variational inference for neural networks, yielding reduced credible intervals and fewer constraint violations on a single-particle battery model versus standard variational Bayesian neural networks.
-
RAYEN: Imposition of Hard Convex Constraints on Neural Networks
RAYEN enforces hard convex constraints (linear, quadratic, SOC, LMI) on neural networks with negligible overhead while guaranteeing satisfaction at all times.
-
Embedding Linear Equality Constraints in Probabilistic Neural Networks for Dynamic Modelling
Probabilistic neural network framework embeds linear equality constraints for dynamic chemical process modeling, showing improved accuracy, calibration, and constraint adherence on reduced data plus faster training on large data.
-
Fusing Backdoors, Machine Learning, and Optimization for Large-Scale Parametric Mixed-Integer Programs
BIPC framework identifies backdoors in parametric MIPs, trains ML models to predict backdoor values or intervals, and solves constrained reduced problems for faster solutions with limited quality loss.
-
Physics-Informed Graph Learning Acceleration for Large-Scale AC-OPF with Topology Changes
GraphOPF applies graph learning with physics-informed self-supervision to solve AC-OPF up to 66 times faster than baselines on large systems including the Korean grid while claiming over 99% feasibility.