Regularizers that penalize big-M constants, unstable neurons, and per-sample LP relaxation gaps during neural network training reduce MILP solve times by up to four orders of magnitude while preserving surrogate accuracy.
arXiv preprint arXiv:2510.25986 (2025)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Relaxation-Informed Training of Neural Network Surrogate Models
Regularizers that penalize big-M constants, unstable neurons, and per-sample LP relaxation gaps during neural network training reduce MILP solve times by up to four orders of magnitude while preserving surrogate accuracy.