arXiv · 2607.11540
Tropical Circuits with Scalar Multiplication Gates
Abstract
We study tropical circuits with scalar multiplication gates, that is, algebraic circuits whose gates implement $\max$, $+$, or multiplication with a positive constant. For such circuits, we prove exponential size lower bounds for computing maximum weight directed spanning trees and maximum weight bipartite perfect matchings. As a corollary, we obtain an exponential size separation between monotone and non-monotone maxout neural networks, which generalize the popularly used ReLU neural networks. One conclusion from this is that neural network models with enforced convexity constraints, such as input-convex neural networks (ICNNs), sometimes need to be exponentially larger than their unrestricted counterparts in order to express the same functions.
Explore related subjects
Keep this discovery
Christoph Hertrich, Moritz Stargalla. 2026-07-13. Tropical Circuits with Scalar Multiplication Gates. https://arxiv.org/abs/2607.11540
Cite the original work for its findings. Save a collection to share your selection of sources.