SOC-ICNN generalizes ReLU-based ICNNs to SOCP, strictly expanding the class of representable convex functions while preserving similar forward-pass complexity.
Parametric Nonconvex Optimization via Convex Surrogates
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
This paper presents a novel learning-based approach to construct a surrogate problem that approximates a given parametric nonconvex optimization problem. The surrogate function is designed to be the minimum of a finite set of functions, given by the composition of convex and monotonic terms, so that the surrogate problem can be solved directly through parallel convex optimization. As a proof of concept, numerical experiments on a nonconvex path tracking problem confirm the approximation quality of the proposed method.
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
SOC-ICNN: From Polyhedral to Conic Geometry for Learning Convex Surrogate Functions
SOC-ICNN generalizes ReLU-based ICNNs to SOCP, strictly expanding the class of representable convex functions while preserving similar forward-pass complexity.