Abstract
Many real-world applications require reasoning over hybrid domains involving combinations of continuous and discrete variables and their relationships. Being able to precisely specify all constraints and their respective importance beforehand is often infeasible for the most experienced designer, let alone for a typical decision maker. In this chapter we discuss Learning Modulo Theories (LMT), a learning framework capable of dealing with hybrid domains by combining structured learning with Satisfiability Modulo Theory (SMT) techniques. LMT incorporates SMT solvers and their extensions for optimization as inference engines within learning algorithms. The learning stage automatically identifies the relevant constraints and their respective weights among a set of candidates. The framework can be cast in the structured-output learning paradigm, where the task is learning the structure of the problem from a set of noisy instances, or as a preference elicitation task, where a decision maker is involved in an interactive optimization loop aimed at generating the most preferred solution. We report experimental results highlighting the potential of the method in automated design and recommendation scenarios.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
We depart from the conventional x/y notation for indicating input/output pairs to avoid name clashes with the x-y coordinate variables.
- 2.
While we write Boolean variables using a first-order syntax for readability, the OMT solver currently requires the grounding of all Boolean predicates.
- 3.
Dataset taken from http://cs.nyu.edu/~roweis/data.html.
- 4.
Our preliminary experimental studies showed that Church is incapable of solving in reasonable time the simple task of generating a pair of blocks conditioned on the fact that they touch somewhere.
- 5.
Unassigned features are catalogue features not appearing in any hard constraint or non-zero weight soft constraint.
- 6.
DM utility functions involving nine complex constraints are quite unrealistic and are considered here just for testing the scalability of the algorithm.
References
Ahmadi, B., Kersting, K., Sanner, S.: Multi-evidence lifted message passing, with application to pagerank and the kalman filter. In: Proceedings of IJCAI 2011, pp. 1152–1158 (2011)
Bakir, G.H., Hofmann, T., Schölkopf, B., Smola, A.J., Taskar, B., Vishwanathan, S.V.N.: Predicting Structured Data (Neural Information Processing). The MIT Press, Cambridge (2007)
Barrett, C., Sebastiani, R., Seshia, S.A., Tinelli, C.: Satisfiability modulo theories, chap. 26, Frontiers in Artificial Intelligence and Applications, pp. 825–885. IOS Press, February 2009
Battiti, R., Brunato, M.: Reactive search optimization: learning while optimizing. In: Gendreau, M., Potvin, J.-Y. (eds.) Handbook of Metaheuristics. International Series in Operations Research & Management Science, vol. 146, pp. 543–571. Springer, New York (2010)
Baumgartner, P., Tinelli, C.: Model evolution with equality modulo built-in theories. In: Bjørner, N., Sofronie-Stokkermans, V. (eds.) CADE 2011. LNCS (LNAI), vol. 6803, pp. 85–100. Springer, Heidelberg (2011). doi:10.1007/978-3-642-22438-6_9
Beldiceanu, N., Simonis, H.: A model seeker extracting global constraint models from positive examples. In: Milano, M. (ed.) CP 2012. LNCS, vol. 7514, pp. 141–157. Springer, Heidelberg (2012). doi:10.1007/978-3-642-33558-7_13
Belle, V., Passerini, A., Van den Broeck, G.: Probabilistic inference in hybrid domains by weighted model integration. In: Proceedings of 24th International Joint Conference on Artificial Intelligence (IJCAI) (2015)
Belle, V., Van den Broeck, G., Passerini, A.: Hashing-based approximate probabilistic inference in hybrid domains. In: Proceedings of the 31st Conference on Uncertainty in Artificial Intelligence (UAI) (2015)
Bengio, Y.: Learning deep architectures for AI. Found. Trends Mach. Learn. 2(1), 1–127 (2009)
Bessiere, C., Coletta, R., Hebrard, E., Katsirelos, G., Lazaar, N., Narodytska, N., Quimper, C.-G., Walsh, T.: Constraint acquisition via partial queries. In: Proceedings of the Twenty-Third International Joint Conference on Artificial Intelligence, IJCAI 2013, pp. 475–481. AAAI Press (2013)
Birlutiu, A., Groot, P., Heskes, T.: Efficiently learning the preferences of people. Mach. Learn. 90, 1–28 (2012)
Bonilla, E., Guo, S., Sanner, S.: Gaussian process preference elicitation. In: Lafferty, J., Williams, C.K.I., Shawe-Taylor, J., Zemel, R.S., Culotta, A. (eds.) Advances in Neural Information Processing Systems, pp. 262–270 (2010)
Boutilier, C., Patrascu, R., Poupart, P., Schuurmans, D.: Constraint-based optimization and utility elicitation using the minimax decision criterion. Artif. Intell. 170(8–9), 686–713 (2006)
Boutilier, C., Regan, K., Viappiani, P.: Simultaneous elicitation of preference features and utility. In: Proceedings of the Twenty-Fourth AAAI Conference on Artificial Intelligence (AAAI 2010), Atlanta, GA, USA. AAAI Press, pp. 1160–1167, July 2010
Braziunas, D.: Computational approaches to preference elicitation. Technical report, Department of Computer Science, University of Toronto (2006)
Braziunas, D., Boutilier, C.: Minimax regret based elicitation of generalized additive utilities. In: Proceedings of the Twenty-Third Conference on Uncertainty in Artificial Intelligence (UAI 2007), Vancouver, pp. 25–32 (2007)
Broecheler, M., Mihalkova, L., Getoor, L.: Probabilistic similarity logic. In: Uncertainty in Artificial Intelligence (UAI), pp. 73–82 (2010)
Burges. C.: A tutorial on support vector machines for pattern recognition. In: Data Mining and Knowledge Discovery, vol. 2. Kluwer Academic Publishers, Boston (1998)
Campigotto, P., Battiti, R., Passerini, A.: Learning modulo theories for preference elicitation in hybrid domains. arXiv (2015)
Chavira, M., Darwiche, A.: On probabilistic inference by weighted model counting. Artif. Intell. 172(6–7), 772–799 (2008)
Choi, J., Amir, E.: Lifted relational variational inference. In: de Freitas, N., Murphy, K.P. (eds.) UAI 2012: Proceedings of the Twenty-Eighth Conference on Uncertainty in Artificial Intelligence, pp. 196–206. AUAI Press (2012)
Choi, J., Guzmn-Rivera, A., Amir, E.: Lifted relational kalman filtering. In: Proceedings of IJCAI 2011, pp. 2092–2099 (2011)
Choi, J., Hill, D., Amir, E.: Lifted inference for relational continuous models. In: UAI 2010: Proceedings of the Twenty-Sixth Conference on Uncertainty in Artificial Intelligence (2010)
Cimatti, A., Franzén, A., Griggio, A., Sebastiani, R., Stenico, C.: Satisfiability modulo the theory of costs: foundations and applications. In: Esparza, J., Majumdar, R. (eds.) TACAS 2010. LNCS, vol. 6015, pp. 99–113. Springer, Heidelberg (2010). doi:10.1007/978-3-642-12002-2_8
Cimatti, A., Griggio, A., Schaafsma, B.J., Sebastiani, R.: A modular approach to MaxSAT modulo theories. In: Järvisalo, M., Van Gelder, A. (eds.) SAT 2013. LNCS, vol. 7962, pp. 150–165. Springer, Heidelberg (2013). doi:10.1007/978-3-642-39071-5_12
Diligenti, M., Gori, M., Maggini, M., Rigutini, L.: Bridging logic and kernel machines. Mach. Learn. 86(1), 57–88 (2012)
Domshlak, C., Hüllermeier, E., Kaci, S., Prade, H.: Preferences in AI: an overview. Artif. Intell. 175(7–8), 1037–1052 (2011)
Fränzle, M., Herde, C., Teige, T., Ratschan, S., Schubert, T.: Efficient solving of large non-linear arithmetic constraint systems with complex boolean structure. JSAT 1(3–4), 209–236 (2007)
Friedman, J., Hastie, T., Rosset, S., Tibshirani, R.: Discussion of boosting papers. Ann. Stat. 32, 102–107 (2004)
Gelain, M., Pini, M., Rossi, F., Venable, K., Wilson, N.: Interval-valued soft constraint problems. Ann. Math. Artif. Intell. 58, 261–298 (2010)
Gelain, M., Pini, M.S., Rossi, F., Venable, K.B., Walsh, T.: Elicitation strategies for soft constraint problems with missing preferences: properties, algorithms and experimental studies. Artif. Intell. J. 174(3–4), 270–294 (2010)
Getoor, L., Taskar, B.: Introduction to Statistical Relational Learning (Adaptive Computation and Machine Learning). The MIT Press, Cambridge (2007)
Goodman, N.D., Mansinghka, V.K., Roy, D.M., Bonawitz, K., Tenenbaum, J.B.: Church: a language for generative models. In: McAllester, D.A., Myllymäki, P. (eds.) UAI, pp. 220–229. AUAI Press (2008)
Griggio, A., Phan, Q.-S., Sebastiani, R., Tomasi, S.: Stochastic local search for SMT: combining theory solvers with WalkSAT. In: Tinelli, C., Sofronie-Stokkermans, V. (eds.) FroCoS 2011. LNCS (LNAI), vol. 6989, pp. 163–178. Springer, Heidelberg (2011). doi:10.1007/978-3-642-24364-6_12
Guo, S., Sanner, S.: Real-time multiattribute Bayesian preference elicitation with pairwise comparison queries. J. Mach. Learn. Res. - Proc. Track 9, 289–296 (2010)
Gutmann, B., Jaeger, M., Raedt, L.: Extending ProbLog with continuous distributions. In: Frasconi, P., Lisi, F.A. (eds.) ILP 2010. LNCS (LNAI), vol. 6489, pp. 76–91. Springer, Heidelberg (2011). doi:10.1007/978-3-642-21295-6_12
Hausner, A.: Simulating decorative mosaics. In: Proceedings of the 28th Annual Conference on Computer Graphics and Interactive Techniques, SIGGRAPH 2001, pp. 573–580. ACM, New York (2001)
Islam, M.A., Ramakrishnan, C.R., Ramakrishnan, I.V.: Inference in probabilistic logic programs with continuous random variables. Theory Pract. Log. Program. 12(4–5), 505–523 (2012)
Joachims, T.: Optimizing search engines using click through data. In: Proceedings of the Eighth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2002, pp. 133–142. ACM, New York (2002)
Joachims, T., Finley, T., Chun-Nam John, Y.: Cutting-plane training of structural SVMs. Mach. Learn. 77(1), 27–59 (2009)
Jovanović, D., Moura, L.: Solving non-linear arithmetic. In: Gramlich, B., Miller, D., Sattler, U. (eds.) IJCAR 2012. LNCS (LNAI), vol. 7364, pp. 339–354. Springer, Heidelberg (2012). doi:10.1007/978-3-642-31365-3_27
Koller, D., Friedman, N.: Probabilistic Graphical Models: Principles and Techniques - Adaptive Computation and Machine Learning. The MIT Press, Cambridge (2009)
Kruglov, E.: Superposition modulo theory. Ph.D. thesis, Universität des Saarlandes, Postfach 151141, 66041 Saarbrücken (2013)
Kuželka, O., Szabóová, A., Holec, M., Železný, F.: Gaussian logic for predictive classification. In: Gunopulos, D., Hofmann, T., Malerba, D., Vazirgiannis, M. (eds.) ECML PKDD 2011. LNCS (LNAI), vol. 6912, pp. 277–292. Springer, Heidelberg (2011). doi:10.1007/978-3-642-23783-6_18
Lallouet, A., Lopez, M., Martin, L., Vrain, C.: On learning constraint problems. In: ICTAI (1) 2010, pp. 45–52 (2010)
Larraz, D., Oliveras, A., Rodríguez-Carbonell, E., Rubio, A.: Minimal-model-guided approaches to solving polynomial constraints and extensions. In: Sinz, C., Egly, U. (eds.) SAT 2014. LNCS, vol. 8561, pp. 333–350. Springer, Heidelberg (2014). doi:10.1007/978-3-319-09284-3_25
LeCun, Y., Chopra, S., Hadsell, R., Ranzato, M., Huang, F.-J.: A tutorial on energy-based learning. In: Bakir, G., Hofman, T., Schölkopf, B., Smola, A., Taskar, B. (eds.) Predicting Structured Data. MIT Press, Cambridge (2006)
Leenen, L., Anbulagan, A., Meyer, T., Ghose, A.: Modeling and solving semiring constraint satisfaction problems by transformation to weighted semiring Max-SAT. In: Orgun, M.A., Thornton, J. (eds.) AI 2007. LNCS (LNAI), vol. 4830, pp. 202–212. Springer, Heidelberg (2007). doi:10.1007/978-3-540-76928-6_22
Li, Y., Albarghouthi, A., Kincad, Z., Gurfinkel, A., Chechik, M.: Symbolic optimization with SMT solvers. In: Proceedings of the 41st ACM SIGPLAN-SIGACT Symposium on Principles of Programming Languages, POPL 2014, pp. 607–618. ACM, New York (2014)
Lippi, M., Frasconi, P.: Prediction of protein-residue contacts by markov logic networks with grounding-specific weights. Bioinformatics 25(18), 2326–2333 (2009)
March, J.G.: Bounded rationality, ambiguity, and the engineering of choice. Bell J. Econ. 9, 587–608 (1978)
McCormack, J., d’Inverno, M. (eds.): Computers and Creativity. Springer, Heidelberg (2012)
Nieuwenhuis, R., Oliveras, A.: On SAT modulo theories and optimization problems. In: Biere, A., Gomes, C.P. (eds.) SAT 2006. LNCS, vol. 4121, pp. 156–169. Springer, Heidelberg (2006). doi:10.1007/11814948_18
Nrman, P., Buschle, M., Knig, J., Johnson, P.: Hybrid probabilistic relational models for system quality analysis. In: EDOC, pp. 57–66. IEEE Computer Society (2010)
Ravkic, I., Ramon, J., Davis, J.: Learning relational dependency networks in hybrid domains. Mach. Learn. 100(2), 217–254 (2015)
Ricci, F., Rokach, L., Shapira, B., Kantor, P.B.: Recommender Systems Handbook, 1st edn. Springer, New York (2010)
Rümmer, P.: A constraint sequent calculus for first-order logic with linear integer arithmetic. In: Cervesato, I., Veith, H., Voronkov, A. (eds.) LPAR 2008. LNCS (LNAI), vol. 5330, pp. 274–289. Springer, Heidelberg (2008). doi:10.1007/978-3-540-89439-1_20
Savage, L.J.: The theory of statistical decision. J. Am. Stat. Assoc. 46(253), 55–67 (1951)
Sebastiani, R.: Lazy satisfiability modulo theories. J. Satisfiability, Boolean Model. Comput., JSAT 3(3–4), 141–224 (2007)
Sebastiani, R., Tomasi, S.: Optimization in SMT with \({\cal{LA}}\)(\(\mathbb{Q}\)) cost functions. In: Gramlich, B., Miller, D., Sattler, U. (eds.) IJCAR 2012. LNCS (LNAI), vol. 7364, pp. 484–498. Springer, Heidelberg (2012). doi:10.1007/978-3-642-31365-3_38
Sebastiani, R., Tomasi, S.: Optimization modulo theories with linear rational costs. ACM Trans. Comput. Logic 16(2), 12:1–12:43 (2015)
Sebastiani, R., Trentin, P.: OptiMathSAT: a tool for optimization modulo theories. In: Kroening, D., Păsăreanu, C.S. (eds.) CAV 2015. LNCS, vol. 9206, pp. 447–454. Springer, Heidelberg (2015). doi:10.1007/978-3-319-21690-4_27
Shawe-Taylor, J., Cristianini, N.: Kernel Methods for Pattern Analysis. Cambridge University Press, New York (2004)
Teso, S., Sebastiani, R., Passerini, A.: Structured learning modulo theories. Artif. Intell. (2015)
Tsochantaridis, I., Joachims, T., Hofmann, T., Altun, Y.: Large margin methods for structured and interdependent output variables. J. Mach. Learn. Res. 6, 1453–1484 (2005)
Vanderplaats, G.N.: Multidiscipline Design Optimization: Textbook. Vanderplaats Research & Development, Incorporated, Colorado Springs (2007)
Viappiani, P.: Monte Carlo methods for preference learning. In: Hamadi, Y., Schoenauer, M. (eds.) LION 6. LNCS, vol. 7219, pp. 503–508. Springer, Heidelberg (2012). doi:10.1007/978-3-642-34413-8_52
Viappiani, P., Boutilier, C.: Optimal Bayesian recommendation sets and myopically optimal choice query sets. In: Advances in Neural Information Processing Systems 23 (NIPS), Vancouver, pp. 2352–2360 (2010)
Wang, J., Domingos, P.: Hybrid Markov logic networks. In: Proceedings of the 23rd National Conference on Artificial Intelligence, vol. 2, AAAI 2008, pp. 1106–1111. AAAI Press (2008)
Yang, Y.-L., Wang, J., Vouga, E., Wonka, P.: Urban pattern: layout design by hierarchical domain splitting. ACM Trans. Graph. 32(6), 181:1–181:12 (2013)
Yu, C.-N.J., Joachims, T.: Learning structural SVMs with latent variables. In: Proceedings of the 26th Annual International Conference on Machine Learning, ICML 2009, pp. 1169–1176. ACM, New York (2009)
Yu, L.-F., Yeung, S.-K., Tang, C.-K., Terzopoulos, D., Chan, T.F., Osher, S.J.: Make it home: automatic optimization of furniture arrangement. ACM Trans. Graph. 30(4), 86:1–86:12 (2011)
Acknowledgments
This chapter builds on a body of work done in collaboration with Paolo Campigotto, Roberto Battiti, Stefano Teso and Roberto Sebastiani.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing AG
About this chapter
Cite this chapter
Passerini, A. (2016). Learning Modulo Theories. In: Bessiere, C., De Raedt, L., Kotthoff, L., Nijssen, S., O'Sullivan, B., Pedreschi, D. (eds) Data Mining and Constraint Programming. Lecture Notes in Computer Science(), vol 10101. Springer, Cham. https://doi.org/10.1007/978-3-319-50137-6_6
Download citation
DOI: https://doi.org/10.1007/978-3-319-50137-6_6
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-50136-9
Online ISBN: 978-3-319-50137-6
eBook Packages: Computer ScienceComputer Science (R0)