ICNN surrogates admit an LP-only embedding whose epigraph plus concave envelope equals the convex hull of the network's graph, enabling a branch-and-bound solver that avoids binary variables.
Optimal transport mapping via input convex neural networks
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
In this paper, we present a novel and principled approach to learn the optimal transport between two distributions, from samples. Guided by the optimal transport theory, we learn the optimal Kantorovich potential which induces the optimal transport map. This involves learning two convex functions, by solving a novel minimax optimization. Building upon recent advances in the field of input convex neural networks, we propose a new framework where the gradient of one convex function represents the optimal transport mapping. Numerical experiments confirm that we learn the optimal transport mapping. This approach ensures that the transport mapping we find is optimal independent of how we initialize the neural networks. Further, target distributions from a discontinuous support can be easily captured, as gradient of a convex function naturally models a {\em discontinuous} transport mapping.
fields
math.OC 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Input convex neural networks as surrogates in mathematical optimisation
ICNN surrogates admit an LP-only embedding whose epigraph plus concave envelope equals the convex hull of the network's graph, enabling a branch-and-bound solver that avoids binary variables.