Abstract
We consider interactive learning and covering problems, in a setting where actions may incur different costs, depending on the response to the action. We propose a natural greedy algorithm for response-dependent costs. We bound the approximation factor of this greedy algorithm in active learning settings as well as in the general setting. We show that a different property of the cost function controls the approximation factor in each of these scenarios. We further show that in both settings, the approximation factor of this greedy algorithm is near-optimal among all greedy algorithms. Experiments demonstrate the advantages of the proposed algorithm in the response-dependent cost setting.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
We may assume without loss of generality that \(u(x,S) = 0\) whenever \((x,y) \in S\).
- 2.
- 3.
References
Cuong, N., Lee, W., Ye, N.: Near-optimal adaptive pool-based active learning with general loss. In: 30th Conference on Uncertainty in Artificial Intelligence (2014)
Dasgupta, S.: Analysis of a greedy active learning strategy. In: NIPS 17, pp. 337–344 (2004)
Feige, U.: A threshold of ln(n) for approximating set cover. J. ACM (JACM) 45(4), 634–652 (1998)
Golovin, D., Krause, A.: Adaptive submodularity: theory and applications in active learning and stochastic optimization. J. Artif. Intell. Res. 42, 427–486 (2011)
Golovin, D., Krause, A., Ray, D.: Near-optimal bayesian active learning with noisy observations. In: NIPS, pp. 766–774 (2010)
Gonen, A., Sabato, S., Shalev-Shwartz, S.: Efficient active learning of halfspaces: an aggressive approach. J. Mach. Learn. Res. 14, 2487–2519 (2013)
Guillory, A., Bilmes, J.A.: Interactive submodular set cover. In: Proceedings of the 27th International Conference on Machine Learning (ICML), pp. 415–422 (2010)
Kapoor, A., Horvitz, E., Basu, S.: Selective supervision: guiding supervised learning with decision-theoretic active learning. In: Proceedings of IJCAI (2007)
Leskovec, J., Kleinberg, J., Faloutsos, C.: Graph evolution: densification and shrinking diameters. ACM Trans. Knowl. Disc. Data (TKDD) 1(1), 2 (2007)
Leskovec, J., Mcauley, J.J.: Learning to discover social circles in ego networks. In: Advances in Neural Information Processing Systems, pp. 539–547 (2012)
Lin, H., Bilmes, J.: A class of submodular functions for document summarization. In: Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, HLT 2011, vol. 1, pp. 510–520 (2011)
McCallum, A.K., Nigam, K.: Employing em and pool-based active learning for text classification. In: ICML (1998)
Mirzasoleiman, B., Karbasi, A., Sarkar, R., Krause, A.: Distributed submodular maximization: identifying representative elements in massive data. In: NIPS, pp. 2049–2057 (2013)
Nemhauser, G.L., Wolsey, L.A., Fisher, M.L.: An analysis of approximations for maximizing submodular set functions. Math. Program. 14(1), 265–294 (1978)
Sabato, S., Sarwate, A.D., Srebro, N.: Auditing: active learning with outcome-dependent query costs. In: Advances in Neural Information Processing Systems 26 (NIPS) (2013)
Sabato, S., Sarwate, A.D., Srebro, N.: Auditing: active learning with outcome-dependent query costs. arXiv preprint arXiv:1306.2347v4 (2015)
Saettler, A., Laber, E., Cicalese, F.: Trading off worst and expected cost in decision tree problems and a value dependent model. arXiv preprint arXiv:1406.3655 (2014)
Saettler, A., Laber, E., Cicalese, F.: Approximating decision trees with value dependent testing costs. Inf. Process. Lett. 115(68), 594–599 (2015)
Wolsey, L.: An analysis of the greedy algorithm for the submodular set covering problem. Combinatorica 2(4), 385–393 (1982)
Acknowledgements
This work was supported in part by the Israel Science Foundation (grant No. 555/15).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this paper
Cite this paper
Sabato, S. (2016). Submodular Learning and Covering with Response-Dependent Costs. In: Ortner, R., Simon, H., Zilles, S. (eds) Algorithmic Learning Theory. ALT 2016. Lecture Notes in Computer Science(), vol 9925. Springer, Cham. https://doi.org/10.1007/978-3-319-46379-7_9
Download citation
DOI: https://doi.org/10.1007/978-3-319-46379-7_9
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-46378-0
Online ISBN: 978-3-319-46379-7
eBook Packages: Computer ScienceComputer Science (R0)