activity
20162026
most citedTowards Lower Bounds on the Depth of ReLU Neural Networks

4 citations · 4 across the 3 of their papers we have counts for

collaborators

6 papers

math.CO2026

The red-blue-yellow matching problem

Manuel Aprile, Marco Di Summa

We consider the red-blue-yellow matching problem: given two natural numbers , and a graph whose edges are colored red, blue or yellow, the goal is to find a matching…

math.OC2022

The role of rationality in integer-programming relaxations

Manuel Aprile, Gennadiy Averkov, Marco Di Summa +1

For a finite set that can be represented as for some polyhedron , we call a relaxation of and define the relaxation co…

cs.LG2021★ 4 cited

Towards Lower Bounds on the Depth of ReLU Neural Networks

Christoph Hertrich, Amitabh Basu, Marco Di Summa +1

We contribute to a better understanding of the class of functions that can be represented by a neural network with ReLU activations and a given architecture. Using techniques from…

math.OC2017

Optimal cutting planes from the group relaxations

Amitabh Basu, Michele Conforti, Marco Di Summa +1

We study quantitative criteria for evaluating the strength of valid inequalities for Gomory and Johnson's finite and infinite group models and we describe the valid inequalities th…

math.OC2017

Extreme functions with an arbitrary number of slopes

Amitabh Basu, Michele Conforti, Marco Di Summa +1

For the one dimensional infinite group relaxation, we construct a sequence of extreme valid functions that are piecewise linear and such that for every natural number , th…

math.OC2016

The structure of the infinite models in integer programming

Amitabh Basu, Michele Conforti, Marco Di Summa +1

The infinite models in integer programming can be described as the convex hull of some points or as the intersection of halfspaces derived from valid functions. In this paper we st…