Abstract
We analyze the expected cost of a greedy active learning algorithm. Our analysis extends previous work to a more general setting in which different queries have different costs. Moreover, queries may have more than two possible responses and the distribution over hypotheses may be non uniform. Specific applications include active learning with label costs, active learning for multiclass and partial label queries, and batch mode active learning. We also discuss an approximate version of interest when there are very many queries.
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 subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Adler, M., Heeringa, B.: Approximating optimal binary decision trees. In: Goel, A., Jansen, K., Rolim, J.D.P., Rubinfeld, R. (eds.) APPROX and RANDOM 2008. LNCS, vol. 5171, pp. 1–9. Springer, Heidelberg (2008)
Beygelzimer, A., Dasgupta, S., Langford, J.: Importance weighted active learning. In: ICML (2009)
Chakaravarthy, V.T., Pandit, V., Roy, S., Awasthi, P., Mohania, M.: Decision trees for entity identification: approximation algorithms and hardness results. In: PODS (2007)
Chakaravarthy, V.T., Pandit, V., Roy, S., Sabharwal, Y.: Approximating decision trees with multiway branches. In: ICALP (2009)
Cover, T.M., Thomas, J.A.: Elements of Information Theory, 2nd edn. Wiley-Interscience, Hoboken (2006)
Dasgupta, S.: Analysis of a greedy active learning strategy. In: NIPS (2004)
Dasgupta, S., Hsu, D., Monteleoni, C.: A general agnostic active learning algorithm. In: NIPS (2007)
Haertel, R., Sepppi, K.D., Ringger, E.K., Carroll, J.L.: Return on investment for active learning. In: NIPS Workshop on Cost-Sensitive Learning (2008)
Hanneke, S.: The cost complexity of interactive learning (unpublished, 2006), http://www.cs.cmu.edu/~shanneke/docs/2006/cost-complexity-working-notes.pdf
Hanneke, S.: Teaching dimension and the complexity of active learning. In: Bshouty, N.H., Gentile, C. (eds.) COLT 2007. LNCS (LNAI), vol. 4539, pp. 66–81. Springer, Heidelberg (2007)
Kosaraju, S.R., Przytycka, T.M., Borgstrom, R.: On an optimal split tree problem. In: Dehne, F., Gupta, A., Sack, J.-R., Tamassia, R. (eds.) WADS 1999. LNCS, vol. 1663, pp. 157–168. Springer, Heidelberg (1999)
Settles, B., Craven, M., Friedland, L.: Active learning with real annotation costs. In: NIPS Workshop on Cost-Sensitive Learning (2008)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Guillory, A., Bilmes, J. (2009). Average-Case Active Learning with Costs. In: Gavaldà, R., Lugosi, G., Zeugmann, T., Zilles, S. (eds) Algorithmic Learning Theory. ALT 2009. Lecture Notes in Computer Science(), vol 5809. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-04414-4_15
Download citation
DOI: https://doi.org/10.1007/978-3-642-04414-4_15
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-04413-7
Online ISBN: 978-3-642-04414-4
eBook Packages: Computer ScienceComputer Science (R0)