{"type":"ScholarlyArticle","title":"Approximation Guarantees of Stochastic Greedy Algorithms for Subset Selection","authors":[{"name":"Chao Qian","slug":"chao-qian","given":"Chao","family":"Qian","affiliation":"Anhui Province Key Lab of Big Data Analysis and Application , University of Science and Technology of China , Hefei 230027 , China"},{"name":"Yang Yu","slug":"yang-yu","given":"Yang","family":"Yu","affiliation":"National Key Lab for Novel Software Technology , Nanjing University , Nanjing 210023 , China"},{"name":"Ke Tang","slug":"ke-tang","given":"Ke","family":"Tang","affiliation":"Shenzhen Key Lab of Computational Intelligence , Department of Computer Science and Engineering , Southern University of Science and Technology , Shenzhen 518055 , China"}],"abstract":"Subset selection is a fundamental problem in many areas, which aims to select the best subset of size at most $k$ from a universe. Greedy algorithms are widely used for subset selection, and have shown good approximation performances in deterministic situations. However, their behaviors are stochastic in many realistic situations (e.g., large-scale and noisy). For general stochastic greedy algorithms, bounded approximation guarantees were obtained only for subset selection with monotone submodular objective functions, while real-world applications often involve non-monotone or non-submodular objective functions and can be subject to a more general constraint than a size constraint. This work proves their approximation guarantees in these cases, and thus largely extends the applicability of stochastic greedy algorithms.","doi":"10.24963/ijcai.2018/205","url":"https://ijcai.org/proceedings/2018/205","pdf":"https://ijcai.org/proceedings/2018/0205.pdf","markdown":"https://ijcai.org/proceedings/2018/205.md","bibtex":"https://ijcai.org/proceedings/2018/bibtex/205","volume":{"slug":"2018","title":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2018","url":"https://ijcai.org/proceedings/2018/","year":2018,"location":"Stockholm","dates":"13-19 July 2018","editors":"Jérôme Lang","isbn":"978-0-9992411-2-7","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2018"},"section":"Heuristic Search and Game Playing","track":"Main track","number":205,"pages":{"first":1478,"last":1484},"keywords":["Heuristic Search and Game Playing: Combinatorial Search and Optimisation","Heuristic Search and Game Playing: Heuristic Search","Heuristic Search and Game Playing: Heuristic Search and Machine Learning"],"videos":[],"references":[{"position":1,"raw":"[Bian et al., 2017] A. A. Bian, J. M. Buhmann, A. Krause, and S. Tschiatschek. Guarantees for greedy maximization of non-submodular functions with applications. In ICML, pages 498-507, 2017.","title":"Guarantees for greedy maximization of non-submodular functions with applications","authors":"A A Bian, J M Buhmann, A Krause, S Tschiatschek","year":"2017","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Buchbinder et al., 2014] N. Buchbinder, M. Feldman, J. S. Naor, and R. Schwartz. Submodular maximization with cardinality constraints. In SODA, pages 1433-1452, 2014.","title":"Submodular maximization with cardinality constraints","authors":"N Buchbinder, M Feldman, J S Naor, R Schwartz","year":"2014","venue":"SODA","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Calinescu et al., 2011] G. Calinescu, C. Chekuri, M. Pál, and J. Vondrák. Maximizing a monotone submodular function subject to a matroid constraint. SIAM Journal on Computing, 40(6):1740-1766, 2011.","title":"Maximizing a monotone submodular function subject to a matroid constraint","authors":"G Calinescu, C Chekuri, M Pál, J Vondrák","year":"2011","venue":"SIAM Journal on Computing","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Das and Kempe, 2011] A. Das and D. Kempe. Submodu- lar meets spectral: Greedy algorithms for subset selection, sparse approximation and dictionary selection. In ICML, pages 1057-1064, 2011.","title":"Submodular meets spectral: Greedy algorithms for subset selection, sparse approximation and dictionary selection","authors":"A Das, D Kempe","year":"2011","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Elenberg et al., 2016] E. R. Elenberg, R. Khanna, A. G. Di- makis, and S. Negahban. Restricted strong convexity im- plies weak submodularity. arXiv:1612.00804, 2016.","title":"Restricted strong convexity implies weak submodularity","authors":"E R Elenberg, R Khanna, A G Dimakis, S Negahban","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Fisher et al., 1978] M. L. Fisher, G. L. Nemhauser, and L. A. Wolsey. An analysis of approximations for maxi- mizing submodular set functions -II. Polyhedral Combi- natorics, pages 73-87, 1978.","title":"An analysis of approximations for maximizing submodular set functions -II","authors":"M L Fisher, G L Nemhauser, L A Wolsey","year":"1978","venue":"Polyhedral Combinatorics","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Hassidim and Singer, 2017] A. Hassidim and Y. Singer. Ro- bust guarantees of stochastic greedy algorithms. In ICML, pages 1424-1432, 2017.","title":"Robust guarantees of stochastic greedy algorithms","authors":"A Hassidim, Y Singer","year":"2017","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Jenkyns, 1976] T. A. Jenkyns. The efficacy of the 'greedy' algorithm. In Proceedings of the 7th Southeastern Con- ference on Combinatorics, Graph Theory and Computing, pages 341-350, 1976.","title":"The efficacy of the 'greedy' algorithm","authors":"T A Jenkyns","year":"1976","venue":"Proceedings of the 7th Southeastern Conference on Combinatorics, Graph Theory and Computing","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Kempe et al., 2003] D. Kempe, J. Kleinberg, and É. Tardos. Maximizing the spread of influence through a social net- work. In KDD, pages 137-146, 2003.","title":"Maximizing the spread of influence through a social network","authors":"D Kempe, J Kleinberg, É Tardos","year":"2003","venue":"KDD","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Khanna et al., 2017] R. Khanna, E. Elenberg, A. Dimakis, S. Negahban, and J. Ghosh. Scalable greedy feature se- lection via weak submodularity. In AISTATS, pages 1560- 1568, 2017.","title":"Scalable greedy feature selection via weak submodularity","authors":"R Khanna, E Elenberg, A Dimakis, S Negahban, J Ghosh","year":"2017","venue":"AISTATS","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Korte and Hausmann, 1978] B. Korte and D. Hausmann. An analysis of the greedy heuristic for independence sys- tems. Annals of Discrete Mathematics, 2:65-74, 1978.","title":"An analysis of the greedy heuristic for independence systems","authors":"B Korte, D Hausmann","year":"1978","venue":"Annals of Discrete Mathematics","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Krause and Guestrin, 2005] A. Krause and C. Guestrin. Near-optimal nonmyopic value of information in graphi- cal models. In UAI, pages 324-331, 2005.","title":"Near-optimal nonmyopic value of information in graphical models","authors":"A Krause, C Guestrin","year":"2005","venue":"UAI","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Krause et al., 2008] A. Krause, A. Singh, and C. Guestrin. Near-optimal sensor placements in Gaussian processes: Theory, efficient algorithms and empirical studies. Jour- nal of Machine Learning Research, 9:235-284, 2008.","title":"Near-optimal sensor placements in Gaussian processes: Theory, efficient algorithms and empirical studies","authors":"A Krause, A Singh, C Guestrin","year":"2008","venue":"Journal of Machine Learning Research","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Kulesza and Taskar, 2012] A. Kulesza and B. Taskar. De- terminantal point processes for machine learning. Foun- dations and Trends in Machine Learning, 5(2-3):123-286, 2012.","title":"Determinantal point processes for machine learning","authors":"A Kulesza, B Taskar","year":"2012","venue":"Foundations and Trends in Machine Learning","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Lawrence et al., 2003] N. Lawrence, M. Seeger, and R. Her- brich. Fast sparse Gaussian process methods: The infor- mative vector machine. In NIPS, pages 625-632, 2003.","title":"Fast sparse Gaussian process methods: The informative vector machine","authors":"N Lawrence, M Seeger, R Herbrich","year":"2003","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Miller, 2002] A. Miller. Subset Selection in Regression. Chapman and Hall/CRC, 2nd edition, 2002.","title":"Subset Selection in Regression","authors":"A Miller","year":"2002","venue":null,"doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Mirzasoleiman et al., 2015] B. Mirzasoleiman, A. Badani- diyuru, A. Karbasi, J. Vondrák, and A. Krause. Lazier than lazy greedy. In AAAI, pages 1812-1818, 2015.","title":"Lazier than lazy greedy","authors":"B Mirzasoleiman, A Badanidiyuru, A Karbasi, J Vondrák, A Krause","year":"2015","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Nemhauser and Wolsey, 1978] G. L. Nemhauser and L. A. Wolsey. Best algorithms for approximating the maximum of a submodular set function. Mathematics of Operations Research, 3(3):177-188, 1978.","title":"Best algorithms for approximating the maximum of a submodular set function","authors":"G L Nemhauser, L A Wolsey","year":"1978","venue":"Mathematics of Operations Research","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Nemhauser et al., 1978] G. L. Nemhauser, L. A. Wolsey, and M. L. Fisher. An analysis of approximations for max- imizing submodular set functions -I. Mathematical Pro- gramming, 14(1):265-294, 1978.","title":"An analysis of approximations for maximizing submodular set functions -I","authors":"G L Nemhauser, L A Wolsey, M L Fisher","year":"1978","venue":"Mathematical Programming","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Ohsaka and Yoshida, 2015] N. Ohsaka and Y. Yoshida. Monotone k-submodular function maximization with size constraints. In NIPS, pages 694-702, 2015.","title":"Monotone k-submodular function maximization with size constraints","authors":"N Ohsaka, Y Yoshida","year":"2015","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Qian et al., 2017a] C. Qian, J.-C. Shi, Y. Yu, and K. Tang. On subset selection with general cost constraints. In IJCAI, pages 2613-2619, 2017.","title":"On subset selection with general cost constraints","authors":"Qian","year":"2017","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2017/364"},{"position":22,"raw":"[Qian et al., 2017b] C. Qian, J.-C. Shi, Y. Yu, K. Tang, and Z.-H. Zhou. Subset selection under noise. In NIPS, pages 3562-3572, 2017.","title":"Subset selection under noise","authors":"Qian","year":"2017","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Singla et al., 2016] A. Singla, S. Tschiatschek, and A. Krause. Noisy submodular maximization via adap- tive sampling with applications to crowdsourced image collection summarization. In AAAI, pages 2037-2043, 2016.","title":"Noisy submodular maximization via adaptive sampling with applications to crowdsourced image collection summarization","authors":"A Singla, S Tschiatschek, A Krause","year":"2016","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Strang, 2006] G. Strang. Linear Algebra and Its Applica- tions. Thomson Learning, 4th edition, 2006.","title":"Linear Algebra and Its Applications","authors":"G Strang","year":"2006","venue":"Thomson Learning","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Zhang and Vorobeychik, 2016] H. Zhang and Y. Vorobey- chik. Submodular optimization with routing constraints. In AAAI, pages 819-826, 2016.","title":"Submodular optimization with routing constraints","authors":"H Zhang, Y Vorobeychik","year":"2016","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Zhou and Spanos, 2016] Y. Zhou and C. Spanos. Causal meets submodular: Subset selection with directed infor- mation. In NIPS, pages 2649-2657, 2016.","title":"Causal meets submodular: Subset selection with directed information","authors":"Y Zhou, C Spanos","year":"2016","venue":"NIPS","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}