{"type":"ScholarlyArticle","title":"Predict+Optimise with Ranking Objectives: Exhaustively Learning Linear Functions","authors":[{"name":"Emir Demirovic","slug":"emir-demirovic","given":"Emir","family":"Demirović","affiliation":"University of Melbourne , Australia"},{"name":"Peter J. Stuckey","slug":"peter-j-stuckey","given":"Peter J.","family":"Stuckey","affiliation":"Monash University , Australia; Data61 , Australia"},{"name":"James Bailey","slug":"james-bailey","given":"James","family":"Bailey","affiliation":"University of Melbourne , Australia"},{"name":"Jeffrey Chan","slug":"jeffrey-chan","given":"Jeffrey","family":"Chan","affiliation":"RMIT University , Australia"},{"name":"Christopher Leckie","slug":"christopher-leckie","given":"Christopher","family":"Leckie","affiliation":"University of Melbourne , Australia"},{"name":"Kotagiri Ramamohanarao","slug":"kotagiri-ramamohanarao","given":"Kotagiri","family":"Ramamohanarao","affiliation":"University of Melbourne , Australia"},{"name":"Tias Guns","slug":"tias-guns","given":"Tias","family":"Guns","affiliation":"Vrije Universiteit Brussel , Belgium"}],"abstract":"We study the predict+optimise problem, where machine learning and combinatorial optimisation must interact to achieve a common goal. These problems are important when optimisation needs to be performed on input parameters that are not fully observed but must instead be estimated using machine learning. Our contributions are two-fold: 1) we provide theoretical insight into the properties and computational complexity of predict+optimise problems in general, and 2) develop a novel framework that, in contrast to related work, guarantees to compute the optimal parameters for a linear learning function given any ranking optimisation problem. We illustrate the applicability of our framework for the particular case of the unit-weighted knapsack predict+optimise problem and evaluate on benchmarks from the literature.","doi":"10.24963/ijcai.2019/151","url":"https://ijcai.org/proceedings/2019/151","pdf":"https://ijcai.org/proceedings/2019/0151.pdf","markdown":"https://ijcai.org/proceedings/2019/151.md","bibtex":"https://ijcai.org/proceedings/2019/bibtex/151","volume":{"slug":"2019","title":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2019","url":"https://ijcai.org/proceedings/2019/","year":2019,"location":"Macao","dates":"10-16 August 2019","editors":"Sarit Kraus","isbn":"978-0-9992411-4-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2019"},"section":"Constraints and SAT","track":"Main track","number":151,"pages":{"first":1078,"last":1085},"keywords":["Constraints and SAT: Constraints and Data Mining ; Machine Learning","Heuristic Search and Game Playing: Combinatorial Search and Optimisation"],"videos":[],"references":[{"position":1,"raw":"[Azizi et al., 2018] Mohammad Javad Azizi, Phebe Vayanos, Bryan Wilder, Eric Rice, and Milind Tambe. Designing fair, efficient, and interpretable policies for prioritizing homeless youth for housing resources. In Integration of Constraint Programming, Artificial Intel- ligence, and Operations Research -15th International Conference, CPAIOR Proceedings, pages 35-51, 2018.","title":"Designing fair, efficient, and interpretable policies for prioritizing homeless youth for housing resources","authors":"Mohammad Javad Azizi, Phebe Vayanos, Bryan Wilder, Eric Rice, Milind Tambe","year":"2018","venue":"Integration of Constraint Programming, Artificial Intelligence, and Operations Research -15th International Conference, CPAIOR Proceedings","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Berman et al., 2016] David Berman, Andre Cire, and Willian van Hoeve. Decisions diagrams for optimization. Springer, 2016.","title":"Decisions diagrams for optimization","authors":"David Berman, Andre Cire, Willian Van Hoeve","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Bessiere et al., 2017] Christian Bessiere, Frédéric Koriche, Nadjib Lazaar, and Barry O'Sullivan. Constraint acquisi- tion. Artificial Intelligence, 244:315 -342, 2017. Com- bining Constraint Solving with Mining and Learning. [Borchani et al., 2015]","title":"Christian Bessiere, Frédéric Koriche, Nadjib Lazaar, and Barry O'Sullivan. Constraint acquisition","authors":"Bessiere","year":"2015","venue":"Combining Constraint Solving with Mining and Learning","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"Hanen Borchani, Gherardo Varando, Concha Bielza, and Pedro Larrañaga. A survey on multi- output regression. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 5(5):216-233, 2015.","title":"A survey on multioutput regression","authors":"Hanen Borchani, Gherardo Varando, Concha Bielza, Pedro Larrañaga","year":"2015","venue":"Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Demirović et al., 2019] Emir Demirović, Peter J. Stuckey, James Bailey, Jeffrey Chan, Chris Leckie, Kotagiri Ra- mamohanarao, and Tias Guns. An investigation into pre- diction + optimisation for the knapsack problem. In Inte- gration of Constraint Programming, Artificial Intelligence, and Operations Research -16th International Conference, CPAIOR, Proceedings, pages 241-257, 2019.","title":"An investigation into prediction + optimisation for the knapsack problem","authors":"Demirović","year":"2019","venue":"Artificial Intelligence, and Operations Research -16th International Conference, CPAIOR, Proceedings","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Donti et al., 2017] Priya L. Donti, Brandon Amos, and J. Zico Kolter. Task-based end-to-end model learning in stochastic optimization. In Proceedings of the 31st Con- ference on Neural Information Processing Systems (NIPS 2017), pages 5484-5494, 2017.","title":"Task-based end-to-end model learning in stochastic optimization","authors":"L Priya, Brandon Donti, J Zico Amos, Kolter","year":"2017","venue":"Proceedings of the 31st Conference on Neural Information Processing Systems (NIPS 2017)","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Dooren et al., 2017] David Van Den Dooren, Thomas Sys, Túlio A. M. Toffolo, Tony Wauters, and Greet Vanden Berghe. Multi-machine energy-aware scheduling. EURO J. Computational Optimization, 5(1-2):285-307, 2017.","title":"Multi-machine energy-aware scheduling","authors":"David Van Den Dooren, Thomas Sys, A M Túlio, Tony Toffolo, Greet Wauters, Berghe Vanden","year":"2017","venue":"EURO J. Computational Optimization","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Dragone et al., 2018] Paolo Dragone, Stefano Teso, and Andrea Passerini. Pyconstruct: Constraint programming meets structured prediction. In Proceedings of the Twenty- Seventh International Joint Conference on Artificial Intel- ligence, IJCAI-18, pages 5823-5825. International Joint Conferences on Artificial Intelligence Organization, 7 2018.","title":"Pyconstruct: Constraint programming meets structured prediction","authors":"Paolo Dragone, Stefano Teso, Andrea Passerini","year":"2018","venue":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, IJCAI-18","doi":null,"url":null,"internal_url":"/proceedings/2018/850"},{"position":9,"raw":"[Elmachtoub and Grigas, 2017] Adam N. Elmachtoub and Paul Grigas. Smart \"predict, then optimize\". Technical report, 2017. https://arxiv.org/pdf/1710.08005.pdf.","title":"Smart \"predict, then optimize","authors":"Adam N Elmachtoub, Paul Grigas","year":"2017","venue":null,"doi":null,"url":"https://arxiv.org/pdf/1710.08005.pdf","internal_url":null},{"position":10,"raw":"[Gilmore and Gomory, 1966] PC Gilmore and Ralph E Go- mory. The theory and computation of knapsack functions. Operations Research, 14(6):1045-1074, 1966.","title":"PC Gilmore and Ralph E Gomory. The theory and computation of knapsack functions","authors":"Gomory Gilmore","year":"1966","venue":"Operations Research","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Grimes et al., 2014] Diarmuid Grimes, Georgiana Ifrim, Barry O'Sullivan, and Helmut Simonis. Analyzing the im- pact of electricity price forecasting on energy cost-aware scheduling. Sustainable Computing: Informatics and Sys- tems, 4(4):276-291, 2014. Special Issue on Energy Aware Resource Management and Scheduling (EARMS).","title":"Analyzing the impact of electricity price forecasting on energy cost-aware scheduling","authors":"Diarmuid Grimes, Georgiana Ifrim, O' Barry, Helmut Sullivan, Simonis","year":"2014","venue":"Sustainable Computing: Informatics and Systems","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Joachims, 1998] Thorsten Joachims. Making large-scale svm learning practical. Technical report, Technical Report, SFB 475: Komplexitätsreduktion in Multivariaten Daten- strukturen, Universität Dortmund, 1998.","title":"Making large-scale svm learning practical","authors":"Thorsten Joachims, Joachims","year":"1998","venue":null,"doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Joachims, 2002] Thorsten Joachims. Optimizing search engines using clickthrough data. In Proceedings of the Eighth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD '02, pages 133-142. ACM, 2002.","title":"Optimizing search engines using clickthrough data","authors":"Thorsten Joachims","year":"2002","venue":"Proceedings of the Eighth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD '02","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Kotthoff, 2014] Lars Kotthoff. Algorithm selection for combinatorial search problems: A survey. AI Magazine, 35(3):48-60, 2014.","title":"Lars Kotthoff. Algorithm selection for combinatorial search problems: A survey","authors":"Kotthoff","year":"2014","venue":"AI Magazine","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Liberto et al., 2016] Giovanni Di Liberto, Serdar Kadioglu, Kevin Leo, and Yuri Malitsky. DASH: dynamic approach for switching heuristics. European Journal of Operational Research, 248(3):943-953, 2016.","title":"DASH: dynamic approach for switching heuristics","authors":"Giovanni Di Liberto, Serdar Kadioglu, Kevin Leo, Yuri Malitsky","year":"2016","venue":"European Journal of Operational Research","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Lombardi et al., 2017] Michele Lombardi, Michela Milano, and Andrea Bartolini. Empirical decision model learning. Artificial Intelligence, 244:343-367, 2017.","title":"Empirical decision model learning","authors":"Michele Lombardi, Michela Milano, Andrea Bartolini","year":"2017","venue":"Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Mathaba et al., 2014] Tebello Mathaba, Xiaohua Xia, and Jiangfeng Zhang. Analysing the economic benefit of elec- tricity price forecast in industrial load scheduling. Electric Power Systems Research, 116:158-165, 2014.","title":"Analysing the economic benefit of electricity price forecast in industrial load scheduling","authors":"Mathaba","year":"2014","venue":"Electric Power Systems Research","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Passerini et al., 2017] Andrea Passerini, Guido Tack, and Tias Guns. Introduction to the special issue on combining constraint solving with mining and learning. Artif. Intell., 244:1-5, 2017.","title":"Introduction to the special issue on combining constraint solving with mining and learning","authors":"Andrea Passerini, Guido Tack, Tias Guns","year":"2017","venue":"Artif. Intell","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Picard-Cantin et al., 2017] Émilie Picard-Cantin, Mathieu Bouchard, Claude-Guy Quimper, and Jason Sweeney. Learning the parameters of global constraints using branch-and-bound. In Principles and Practice of Con- straint Programming -23rd International Conference, CP 2017, Melbourne, VIC, Australia, August 28 -September 1, 2017, Proceedings, pages 512-528, 2017.","title":"Learning the parameters of global constraints using branch-and-bound","authors":"Émilie Picard-Cantin, Mathieu Bouchard, Claude-Guy Quimper, Jason Sweeney","year":"2017","venue":"Principles and Practice of Constraint Programming -23rd International Conference, CP 2017","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Pisinger and Røpke, 2010] David Pisinger and Stefan Røpke. Large neighborhood search. In Michel Gendreau and Jean-Yves Potvin, editors, Handbook of Metaheuris- tics, volume 146 of International Series in Operations Research & Management Science, chapter 13, pages 399-420. Springer, 2nd edition, 2010.","title":"Large neighborhood search","authors":"David Pisinger, Stefan Røpke","year":"2010","venue":"Handbook of Metaheuristics","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Teso et al., 2016] Stefano Teso, Andrea Passerini, and Paolo Viappiani. Constructive preference elicitation by setwise max-margin learning. In Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, IJCAI, pages 2067-2073, 2016.","title":"Constructive preference elicitation by setwise max-margin learning","authors":"Stefano Teso, Andrea Passerini, Paolo Viappiani","year":"2016","venue":"Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2016/295"},{"position":22,"raw":"Wilder et al., ] Bryan Wilder, Bistra Dilkina, and Milind Tambe. Melding the data-decisions pipeline: Decision- focused learning for combinatorial optimization. In Pro- ceedings of the Thirty-Third AAAI Conference on Artificial Intelligence (AAAI-19).","title":"Melding the data-decisions pipeline: Decisionfocused learning for combinatorial optimization","authors":"Wilder","year":null,"venue":"Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence (AAAI-19)","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Yue et al., 2007] Yisong Yue, Thomas Finley, Filip Radlin- ski, and Thorsten Joachims. A support vector method for optimizing average precision. In Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval, pages 271-278. ACM, 2007.","title":"A support vector method for optimizing average precision","authors":"Yue","year":"2007","venue":"Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}