Surviving Solver Sensitivity: An ASP Practitioner's Guide (2012)
Bryan Silverthorn, Yuliya Lierler and Marius Schneider
Answer set programming (ASP) is a declarative programming formalism that allows a practitioner to specify a problem without describing an algorithm for solving it. In ASP, the tools for processing problem specifications are called answer set solvers. These systems often require significant computational effort to succeed. Furthermore, they offer different heuristics, expose numerous parameters, and it is well known that their running time is sensitive to the configuration used. Portfolio solvers and automatic algorithm configuration systems are recent attempts to automate the problem of manual parameter tuning, and to mitigate the burden of identifying the right solver configuration. The approaches taken in portfolio solvers and automatic algorithm configuration systems are orthogonal. This paper evaluates these approaches, separately and jointly, in the context of real-world ASP application development. It outlines strategies for their use in such settings, identifies their respective strengths and weaknesses, and advocates for a methodology that would make them an integral part of developing ASP applications.
In International Conference on Logic Programming (ICLP), 2012.

Yuliya Lierler ylierler [at] unomaha edu
Bryan Silverthorn Ph.D. Alumni bsilvert [at] cs utexas edu

The borg project includes a practical algorithm...