Learning Probabilistic Systems from Tree Samples

We consider the problem of learning a non-deterministic probabilistic system consistent with a given finite set of positive and negative tree samples. Consistency is defined with respect to strong simulation conformance. We propose learning algorithms that use traditional and a new stochastic state-space partitioning, the latter resulting in the minimum number of states. We then use them to solve the problem of active learning, that uses a knowledgeable teacher to generate samples as counterexamples to simulation equivalence queries. We show that the problem is undecidable in general, but that it becomes decidable under a suitable condition on the teacher which comes naturally from the way samples are generated from failed simulation checks. The latter problem is shown to be undecidable if we impose an additional condition on the learner to always conjecture a minimum state hypothesis. We therefore propose a semi-algorithm using stochastic partitions. Finally, we apply the proposed (semi-) algorithms to infer intermediate assumptions in an automated assume-guarantee verification framework for probabilistic systems.

[1]  Sagar Chaki,et al.  Automated Assume-Guarantee Reasoning for Simulation Conformance , 2005, CAV.

[2]  Thomas A. Henzinger,et al.  Compositional Methods for Probabilistic Systems , 2001, CONCUR.

[3]  José Oncina,et al.  Learning deterministic regular grammars from stochastic samples in polynomial time , 1999, RAIRO Theor. Informatics Appl..

[4]  Edmund M. Clarke,et al.  Assume-Guarantee Abstraction Refinement for Probabilistic Systems , 2012, CAV.

[5]  Lu Feng,et al.  Learning-Based Compositional Verification for Synchronous Probabilistic Systems , 2011, ATVA.

[6]  Joao Marques-Silva,et al.  Efficient search techniques for the inference of minimum size finite automata , 1998, Proceedings. String Processing and Information Retrieval: A South American Symposium (Cat. No.98EX207).

[7]  Pedro García,et al.  IDENTIFYING REGULAR LANGUAGES IN POLYNOMIAL TIME , 1993 .

[8]  Lijun Zhang,et al.  Decision algorithms for probabilistic simulations , 2009 .

[9]  Jorge Calera-Rubio,et al.  Stochastic Inference of Regular Tree Languages , 2004, Machine Learning.

[10]  Azaria Paz,et al.  Probabilistic automata , 2003 .

[11]  Colin de la Higuera,et al.  Learning Stochastic Finite Automata , 2004, ICGI.

[12]  Mahesh Viswanathan,et al.  A counterexample-guided abstraction-refinement framework for markov decision processes , 2008, TOCL.

[13]  Carl H. Smith,et al.  Inductive Inference: Theory and Methods , 1983, CSUR.

[14]  Eyal Kushilevitz,et al.  Learning functions represented as multiplicity automata , 2000, JACM.

[15]  Amir Pnueli,et al.  In Transition From Global to Modular Temporal Reasoning about Programs , 1989, Logics and Models of Concurrent Systems.

[16]  Robin Milner,et al.  An Algebraic Definition of Simulation Between Programs , 1971, IJCAI.

[17]  Yih-Kuen Tsay,et al.  Learning Minimal Separating DFA's for Compositional Verification , 2009, TACAS.

[18]  H SmithCarl,et al.  Inductive Inference: Theory and Methods , 1983 .

[19]  Wen-Guey Tzeng,et al.  Learning Probabilistic Automata and Markov Chains via Queries , 1992, Machine Learning.

[20]  Edmund M. Clarke,et al.  Compositional model checking , 1989, [1989] Proceedings. Fourth Annual Symposium on Logic in Computer Science.

[21]  Edmund M. Clarke,et al.  Model Checking , 1999, Handbook of Automated Reasoning.

[22]  Kim G. Larsen,et al.  Learning Probabilistic Automata for Model Checking , 2011, 2011 Eighth International Conference on Quantitative Evaluation of SysTems.

[23]  Howard Barringer,et al.  Learning to divide and conquer: applying the L* algorithm to automate assume-guarantee reasoning , 2008, Formal Methods Syst. Des..

[24]  E. Mark Gold,et al.  Complexity of Automaton Identification from Given Data , 1978, Inf. Control..

[25]  Kenneth L. McMillan,et al.  Automated assumption generation for compositional verification , 2007, Formal Methods Syst. Des..

[26]  Hongyang Qu,et al.  Assume-Guarantee Verification for Probabilistic Systems , 2010, TACAS.

[27]  Lu Feng,et al.  Automated Learning of Probabilistic Assumptions for Compositional Reasoning , 2011, FASE.

[28]  Christel Baier,et al.  Probabilistic ω-automata , 2012, JACM.

[29]  Christel Baier,et al.  Deciding Bisimilarity and Similarity for Probabilistic Processes , 2000, J. Comput. Syst. Sci..

[30]  J. Oncina Inference of recognizable tree sets , 2003 .

[31]  Dana Angluin,et al.  Learning Regular Sets from Queries and Counterexamples , 1987, Inf. Comput..

[32]  Nancy A. Lynch,et al.  Probabilistic Simulations for Probabilistic Processes , 1994, Nord. J. Comput..