Abstract
This chapter presents the concept of Continuous Search, the objective of which is to allow any user to eventually get their constraint solver to achieve top performance on their problems. Continuous Search comes in two modes: the functioning mode solves the user’s problem instances using the current heuristics model; the exploration mode reuses these instances to train and improve the heuristics model through machine learning during the computer idle time. Contrasting with previous approaches, Continuous Search thus does not require that the representative instances needed to train a good heuristics model be available beforehand. It achieves lifelong learning, gradually becoming an expert on the user’s problem instance distribution. Experimental validation suggests that Continuous Search can design efficient mixed strategies after considering a moderate number of problem instances.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Out of eight categories, detailed in http://www.gecode.org/doc-latest/reference/classGecode_1_1PropCost.html.
- 2.
The rationale for this decision is that the margin, i.e., the distance of the example w.r.t. the separating hyperplane, is interpreted as the confidence of the prediction [Vap95].
- 3.
- 4.
- 5.
- 6.
References
A. Arbelaez, Y. Hamadi, M. Sebag, Online heuristic selection in constraint programming, in International Symposium on Combinatorial Search, Lake Arrowhead, USA, 2009
A. Arbelaez, Y. Hamadi, M. Sebag, Continuous search in constraint programming, in 22nd IEEE International Conference on Tools with Artificial Intelligence, ICTAI 2010 (IEEE Comput. Soc., Los Alamitos, 2010), pp. 53–60
R. Akbani, S. Kwek, N. Japkowicz, Applying support vector machines to imbalanced datasets, in ECML, ed. by J.F. Boulicaut, F. Esposito, F. Giannotti, D. Pedreschi. Lecture Notes in Computer Science, vol. 3201 (Springer, Berlin, 2004), pp. 39–50
C. Ansótegui, M. Sellmann, K. Tierney, A gender-based genetic algorithm for the automatic configuration of algorithms, in 15th International Conference on Principles and Practice of Constraint Programming, Lisbon, Portugal, ed. by I.P. Gent. LNCS, vol. 5732 (Springer, Berlin, 2009), pp. 142–157
F. Boussemart, F. Hemery, C. Lecoutre, L. Sais, Boosting systematic search by weighting constraints, in Proceedings of the 16th European Conference on Artificial Intelligence, Valencia, Spain, ed. by R.L. de Mántaras, L. Saitta (IOS Press, Amsterdam, 2004), pp. 146–150
T. Carchrae, J.C. Beck, Applying machine learning to low-knowledge control of optimization algorithms. Comput. Intell. 21(4), 372–387 (2005)
M. Correira, P. Barahona, On the efficiency of impact based heuristics, in 14th International Conference on Principles and Practice of Constraint Programming, Sydney, Australia, ed. by P.J. Stuckey. LNCS, vol. 5202 (Springer, Berlin, 2008), pp. 608–612
N. Christianini, J. Shawe-Taylor, An Introduction to Support Vector Machines and Other Kernel-Based Learning Methods (Cambridge University Press, Cambridge, 2000)
S. Epstein, E. Freuder, R. Wallace, A. Morozov, B. Samuels, The adaptive constraint engine, in Principles and Practice of Constraint Programming—CP 2002, 8th International Conference. Lecture Notes in Computer Science, vol. 2470 (Springer, Berlin, 2002), pp. 525–542
Gecode Team, Gecode: GenE. Constraint development environment (2006). Available from http://www.gecode.org
S. Gelly, D. Silver, Combining online and offline knowledge in UCT, in Proceedings of the Twenty-Fourth International Conference on Machine Learning, Corvallis, Oregon, USA, ed. by Z. Ghahramani. ACM International Conference Proceeding Series, vol. 227 (ACM, New York, 2007), pp. 273–280
C. Gomes, B. Selman, H. Kautz, Boosting combinatorial search through randomization, in AAAI/IAAI (1998), pp. 431–437
R.M. Haralick, G.L. Elliott, Increasing tree search efficiency for constraint satisfaction problems, in IJCAI, San Francisco, CA, USA (1979), pp. 356–364
F. Hutter, Y. Hamadi, Parameter adjustment based on performance prediction: towards an instance-aware problem solver. Technical Report MSR-TR-2005-125, Microsoft Research, Cambridge, UK (2005)
F. Hutter, Y. Hamadi, H. Hoos, K. Leyton-Brown, Performance prediction and automated tuning of randomized and parametric algorithms, in CP, ed. by F. Benhamou. Lecture Notes in Computer Science, vol. 4204 (Springer, Berlin, 2006), pp. 213–228
F. Hutter, H. Hoos, K. Leyton-Brown, T. Stützle, ParamILS: an automatic algorithm configuration framework. J. Artif. Intell. Res. 36, 267–306 (2009)
S. Haim, T. Walsh, Restart strategy selection using machine learning techniques, in 12th International Conference on Theory and Applications of Satisfiability Testing, Swansea, UK, ed. by O. Kullmann. LNCS, vol. 5584 (Springer, Berlin, 2009), pp. 312–325
H.A. Kautz, E. Horvitz, Y. Ruan, C.P. Gomes, B. Selman, Dynamic restart policies, in AAAI/IAAI (2002), pp. 674–681
H. Larochelle, Y. Bengio, Classification using discriminative restricted Boltzmann machines, in Proceedings of the Twenty-Fifth International Conference on Machine Learning, Helsinki, Finland, ed. by W.W. Cohen, A. McCallum, S.T. Roweis. ACM International Conference Proceeding Series, vol. 307 (ACM, New York, 2008), pp. 536–543
E. O’Mahony, E. Hebrard, A. Holland, C. Nugent, B. O’Sullivan, Using case-based reasoning in an algorithm portfolio for constraint solving, in Proceedings of the 19th Irish Conference on Artificial Intelligence and Cognitive Science (2008)
I. Rish, M. Brodie, S. Ma et al., Adaptive diagnosis in distributed systems. IEEE Trans. Neural Netw. 16, 1088–1109 (2005)
P. Refalo, Impact-based search strategies for constraint programming, in 10th International Conference on Principles and Practice of Constraint Programming, Toronto, Canada, ed. by M. Wallace. LNCS, vol. 2004 (Springer, Berlin, 2004), pp. 557–571
M. Streeter, D. Golovin, S.F. Smith, Combining multiple heuristics online, in Proceedings of the Twenty-Second AAAI Conference on Artificial Intelligence, Vancouver, British Columbia, Canada (AAAI Press, Menlo Park 2007), pp. 1197–1203
H. Samulowitz, R. Memisevic, Learning to solve QBF, in Proceedings of the Twenty-Second AAAI Conference on Artificial Intelligence, Vancouver, British Columbia (AAAI Press, Menlo Park 2007)
K. Smith-Miles, Cross-disciplinary perspectives on meta-learning for algorithm selection. ACM Comput. Surv. 41(1), 1–25 (2008)
V. Vapnik, The Nature of Statistical Learning (Springer, New York, 1995)
I.H. Witten, E. Frank, Data Mining—Practical Machine Learning Tools and Techniques (Elsevier, Amsterdam, 2005)
H. Wu, P. van Beek, Portfolios with deadlines for backtracking search. Int. J. Artif. Intell. Tools 17(5), 835–856 (2008)
L. Xu, F. Hutter, H. Hoos, K. Leyton-Brown, SATzilla-07: the design and analysis of an algorithm portfolio for SAT, in Principles and Practice of Constraint Programming—CP 2007 (2007)
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Hamadi, Y. (2013). Continuous Search. In: Combinatorial Search: From Algorithms to Systems. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-41482-4_6
Download citation
DOI: https://doi.org/10.1007/978-3-642-41482-4_6
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-41481-7
Online ISBN: 978-3-642-41482-4
eBook Packages: Computer ScienceComputer Science (R0)