AI RESEARCH
SOC-ICNN: From Polyhedral to Conic Geometry for Learning Convex Surrogate Functions
arXiv CS.LG
•
ArXi:2604.22355v1 Announce Type: new 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 representational capacity to piecewise-linear polyhedral functions. To overcome this representational bottleneck, we propose the SOC-ICNN, an architecture that generalizes the underlying optimization class from LP to Second-Order Cone Programming (SOCP). By explicitly injecting positive semi-definite curvature and Euclidean norm-based conic primitives, our formulation.