Adaptive Clause Weight Redistribution
In recent years, dynamic local search (DLS) clause weighting algorithms have emerged as the local search state-of-the-art for solving propositional satisfiability problems. However, most DLS algorithms require the tuning of domain dependent parameters before their performance becomes competitive. If manual parameter tuning is impractical then various mechanisms have been developed that can automatically adjust a parameter value during the search. To date, the most effective adaptive clause weighting algorithm is RSAPS. However, RSAPS is unable to convincingly outperform the best non-weighting adaptive algorithm AdaptNovelty + , even though manually tuned clause weighting algorithms can routinely outperform the Novelty + heuristic on which AdaptNovelty + is based.
In this study we introduce R+DDFW + , an enhanced version of the DDFW clause weighting algorithm developed in 2005, that not only adapts the total amount of weight according to the degree of stagnation in the search, but also incorporates the latest resolution-based preprocessing approach used by the winner of the 2005 SAT competition (R+ AdaptNovelty + ). In an empirical study we show R+DDFW + improves on DDFW and outperforms the other leading adaptive (R+Adapt-Novelty + , R+RSAPS) and non-adaptive (R+G2WSAT) local search solvers over a range of random and structured benchmark problems.
Unable to display preview. Download preview PDF.
- 1.Morris, P.: The Breakout method for escaping from local minima. In: Proceedings of 11th AAAI, pp. 40–45 (1993)Google Scholar
- 2.Cha, B., Iwama, K.: Adding new clauses for faster local search. In: Proceedings of 13th AAAI, pp. 332–337 (1996)Google Scholar
- 3.Frank, J.: Learning short-term clause weights for GSAT. In: Proceedings of 15th IJCAI, pp. 384–389 (1997)Google Scholar
- 4.McAllester, D., Selman, B., Kautz, H.: Evidence for invariants in local search. In: Proceedings of 14th AAAI, pp. 321–326 (1997)Google Scholar
- 5.Wu, Z., Wah, B.: An efficient global-search strategy in discrete Lagrangian methods for solving hard satisfiability problems. In: Proceedings of 17th AAAI, pp. 310–315 (2000)Google Scholar
- 6.Schuurmans, D., Southey, F.: Local search characteristics of incomplete SAT procedures. In: Proceedings of 10th AAAI, pp. 297–302 (2000)Google Scholar
- 8.Thornton, J., Pham, D.N., Bain, S., Ferreira Jr., V.: Additive versus multiplicative clause weighting for SAT. In: Proceedings of 19th AAAI, pp. 191–196 (2004)Google Scholar
- 9.Hoos, H.: An adaptive noise mechanism for WalkSAT. In: Proceedings of 19th AAAI, pp. 655–660 (2002)Google Scholar
- 11.Schuurmans, D., Southey, F., Holte, R.: The exponentiated subgradient algorithm for heuristic boolean programming. In: Proceedings of 17th IJCAI, pp. 334–341 (2001)Google Scholar
- 12.Anbulagan, Pham, D., Slaney, J., Sattar, A.: Old resolution meets modern SLS. In: Proceedings of 20th AAAI, pp. 354–359 (2005)Google Scholar
- 13.Li, C.M., Huang, W.: Diversification and determinism in local search for satisfiability. In: Proceedings of 8th SAT, pp. 158–172 (2005)Google Scholar
- 14.Mills, P., Tsang, E.: Guided local search applied to the satisfiability (SAT) problem. In: Proceedings of 15th ASOR, pp. 872–883 (1999)Google Scholar
- 15.Thornton, J.: Clause weighting local search for SAT. Journal of Automated Reasoning (to appear, 2006)Google Scholar
- 16.Hutter, F., Hamadi, Y.: Parameter adjustment based on performance prediction: Towards an instance aware problem solver. Technical Report: MSR-TR-2005-125, Microsoft Research, WA (2005)Google Scholar