convex neural networks 1exponential lower bounds 1maxout neural networks 1scalar multiplication gates 1tropical circuits 1
From the 1 of 3 linked papers with an AI index.
3 papers
cs.CC2026
Parameterized Complexity of -Lipschitz Constants for Input Convex Neural Networks and -Norm Maximization over Zonotopes
Aritra Das, Vincent Froese, Moritz Grillo +6
Lipschitz constants are a standard way to quantify the sensitivity of neural networks to small input perturbations, but computing them is difficult even for shallow ReLU networks.…
cs.CC2026
Tropical Circuits with Scalar Multiplication Gates
Christoph Hertrich, Moritz Stargalla
The paper studies tropical circuits that include scalar multiplication gates and proves exponential size lower bounds for computing maximum‑weight directed spanning trees and bipar…
cs.CC2026
Parameterized Hardness of Zonotope Containment and Neural Network Verification
Vincent Froese, Moritz Grillo, Christoph Hertrich +1
Neural networks with ReLU activations are a widely used model in machine learning. It is thus important to have a profound understanding of the properties of the functions computed…