ReLU Neural Networks for Exact Maximum Flow Computation

02/12/2021
by   Christoph Hertrich, et al.
0

Understanding the great empirical success of artificial neural networks (NNs) from a theoretical point of view is currently one of the hottest research topics in computer science. In this paper we study the expressive power of NNs with rectified linear units from a combinatorial optimization perspective. In particular, we show that, given a directed graph with n nodes and m arcs, there exists an NN of polynomial size that computes a maximum flow from any possible real-valued arc capacities as input. To prove this, we develop the pseudo-code language Max-Affine Arithmetic Programs (MAAPs) and show equivalence between MAAPs and NNs concerning natural complexity measures. We then design a MAAP to exactly solve the Maximum Flow Problem, which translates to an NN of size 𝒪(m^2 n^2).

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/21/2021

Modeling the AC Power Flow Equations with Optimally Compact Neural Networks: Application to Unit Commitment

Nonlinear power flow constraints render a variety of power system optimi...
research
05/29/2023

Minimum Width of Leaky-ReLU Neural Networks for Uniform Universal Approximation

The study of universal approximation properties (UAP) for neural network...
research
10/26/2018

Using stigmergy to incorporate the time into artificial neural networks

A current research trend in neurocomputing involves the design of novel ...
research
10/13/2010

Combinatorial Continuous Maximal Flows

Maximum flow (and minimum cut) algorithms have had a strong impact on co...
research
01/29/2023

On Enhancing Expressive Power via Compositions of Single Fixed-Size ReLU Network

This paper studies the expressive power of deep neural networks from the...
research
06/14/2022

Tailored max-out networks for learning convex PWQ functions

Convex piecewise quadratic (PWQ) functions frequently appear in control ...
research
01/30/2015

A Proximal Bregman Projection Approach to Continuous Max-Flow Problems Using Entropic Distances

One issue limiting the adaption of large-scale multi-region segmentation...

Please sign up or login with your details

Forgot password? Click here to reset