cs.LG, math.OC, stat.ML

SOC-ICNN: From Polyhedral to Conic Geometry for Learning Convex Surrogate Functions

arXiv:2604.22355v1 Announce Type: cross
Abstract: Classical ReLU-based Input Convex Neural Networks (ICNNs) are equivalent to the optimal value functions of Linear Programming (LP). This intrinsic structural equivalence restricts their representationa…