A Logical Deduction Based Clause Learning Algorithm for Boolean Satisfiability Problems

Clause learning is the key component of modern SAT solvers, while conflict analysis based on the implication graph is the mainstream technology to generate the learnt clauses. Whenever a clause in the clause database is falsified by the current variable assignments, the SAT solver will try to analyze the reason by using different cuts (i.e., the Unique Implication Points) on the implication graph. Those schemes reflect only the conflict on the current search subspace, does not reflect the inherent conflict directly involved in the rest space. In this paper, we propose a new advanced clause learning algorithm based on the conflict analysis and the logical deduction, which reconstructs a liner logical deduction by analyzing the relationship of different decision variables between the backjumping level and the current decision level. The logical deduction result is then added into the clause database as a newly learnt clause. The resulting implementation in Minisat improves the state-of-the-art performance in SAT solving.

[1]  Chanseok Oh.  Patching MiniSat to Deliver Performance of Modern SAT Solvers , 2015 .

[2]  Armin Biere,et al.  Evaluating CDCL Variable Scoring Schemes , 2015, SAT.

[3]  Armin Biere.  Adaptive Restart Strategies for Conflict Driven SAT Solvers , 2008, SAT.

[4]  Joao Marques-Silva,et al.  GRASP-A new search algorithm for satisfiability , 1996, Proceedings of International Conference on Computer Aided Design.

[5]  Hilary Putnam,et al.  A Computing Procedure for Quantification Theory , 1960, JACM.

[6]  Joao Marques-Silva,et al.  GRASP: A Search Algorithm for Propositional Satisfiability , 1999, IEEE Trans. Computers.

[7]  Bart Selman,et al.  Boosting Combinatorial Search Through Randomization , 1998, AAAI/IAAI.

[8]  Donald W. Loveland,et al.  A machine program for theorem-proving , 2011, CACM.

[9]  Inês Lynce,et al.  Conflict-Driven Clause Learning SAT Solvers , 2009, Handbook of Satisfiability.

[10]  Lakhdar Sais,et al.  Learning for Dynamic Subsumption , 2009, 2009 21st IEEE International Conference on Tools with Artificial Intelligence.

[11]  Sharad Malik,et al.  Chaff: engineering an efficient SAT solver , 2001, Proceedings of the 38th Design Automation Conference (IEEE Cat. No.01CH37232).

[12]  E. Goldberg,et al.  BerkMin: A fast and robust SAT-solver , 2002, Proceedings 2002 Design, Automation and Test in Europe Conference and Exhibition.

[13]  Armando Tacchella,et al.  Theory and Applications of Satisfiability Testing , 2003, Lecture Notes in Computer Science.

[14]  Jingchao Chen.  A Bit-Encoding Phase Selection Strategy for Satisfiability Solvers , 2014, TAMC.

[15]  Sebastian Fischmeister,et al.  Impact of Community Structure on SAT Solver Performance , 2014, SAT.

[16]  Niklas Sörensson,et al.  An Extensible SAT-solver , 2003, SAT.

[17]  Roberto J. Bayardo,et al.  Using CSP Look-Back Techniques to Solve Real-World SAT Instances , 1997, AAAI/IAAI.

[18]  J. A. Robinson,et al.  A Machine-Oriented Logic Based on the Resolution Principle , 1965, JACM.

[19]  Gilles Audemard,et al.  Predicting Learnt Clauses Quality in Modern SAT Solvers , 2009, IJCAI.

[20]  Richard C. T. Lee,et al.  Symbolic logic and mechanical theorem proving , 1973, Computer science classics.

[21]  Stephen A. Cook,et al.  The complexity of theorem-proving procedures , 1971, STOC.

[22]  Lakhdar Sais,et al.  A Generalized Framework for Conflict Analysis , 2008, SAT.

[23]  Jinbo Huang,et al.  The Effect of Restarts on the Efficiency of Clause Learning , 2007, IJCAI.

[24]  Krzysztof Czarnecki,et al.  Learning Rate Based Branching Heuristic for SAT Solvers , 2016, SAT.

[25]  Qingshan Chen,et al.  A HEURISTIC COMPLETE ALGORITHM FOR SAT PROBLEM BY USING LOGIC DEDUCTION , 2016 .