A neural network that produces inexact ADMM subproblem solutions for convex quadratic programs is shown to converge under learned residual conditions, and runs faster than Gurobi, SCS, and OSQP on synthetic benchmarks, though the conditions are violated on some instances.
Inexact interior-point method
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A Learning-Based Inexact ADMM for Solving Quadratic Programs
A neural network that produces inexact ADMM subproblem solutions for convex quadratic programs is shown to converge under learned residual conditions, and runs faster than Gurobi, SCS, and OSQP on synthetic benchmarks, though the conditions are violated on some instances.