Solving Integer Quadratic Programming via Explicit and Structural Restrictions

  • Eduard Eiben University of Bergen
  • Robert Ganian Vienna University of Technology
  • Dusan Knop TU Berlin
  • Sebastian Ordyniak University of Sheffield

Abstract

We study the parameterized complexity of Integer Quadratic Programming under two kinds of restrictions: explicit restrictions on the domain or coefficients, and structural restrictions on variable interactions. We argue that both kinds of restrictions are necessary to achieve tractability for Integer Quadratic Programming, and obtain four new algorithms for the problem that are tuned to possible explicit restrictions of instances that we may wish to solve. The presented algorithms are exact, deterministic, and complemented by appropriate lower bounds.

Published
2019-07-17
Section
AAAI Technical Track: Constraint Satisfaction and Optimization