Abstract
We introduce a new feature to inference and learning which we call robustness. By robustness we intuitively model the case that the observation of the learner might be corrupted. We survey a new and novel approach to model such possible corruption as a zero-sum game between an adversary that selects the corruption and a leaner that predict the correct label. The corruption of the observations is done in a worse-case setting, by an adversary, where the main restriction is that the adversary is limited to use one of a fixed know class of modification functions. The main focus in this line of research is on efficient algorithms both for the inference setting and for the learning setting. In order to be efficient in the dimension of the domain, one cannot hope to inspect all the possible inputs. For this, we have to invoke local computation algorithms, that inspect only a logarithmic fraction of the domain per query.
This research was supported in part by The Israeli Centers of Research Excellence (I-CORE) program, (Center No. 4/11), by a grant from the Israel Science Foundation (ISF), by a grant from United States-Israel Binational Science Foundation (BSF).
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.
One can clearly map the dynamic setting to the static setting, by encoding the adversary action in the modification rules, but this will imply that the number of modifications rules would be \(m^{|\mathcal{X}|}\).
- 2.
This also implicitly implies that in the dynamic setting \(|\mathcal{X}|/m\le |\mathcal{Z}|\le m |\mathcal{X}|\).
References
Alon, N., Rubinfeld, R., Vardi, S., Xie, N.: Space-efficient local computation algorithms. In: SODA, pp. 1132–1139 (2012)
Angluin, D., Laird, P.: Learning from noisy examples. Mach. Learn. 2(4), 343–370 (1988)
Ben-Or, M., Linial, N.: Collective coin flipping, robust voting schemes and minima of banzhaf values. In: FOCS, pp. 408–416 (1985)
Ben-Tal, A., El Ghaoui, L., Nemirovski, A.S.: Robust Optimization. Princeton Series in Applied Mathematics. Princeton University Press, Princeton (2009)
Even, G., Medina, M., Ron, D.: Best of two local models: local centralized and local distributed algorithms. In: CoRR, abs/1402.3796 (2014)
Feige, U., Mansour, Y., Schapire, R.: Learning and inference in the presence of corrupted inputs. In: COLT (2015)
Kahn, J., Kalai, G., Linial, N.: The influence of variables on boolean functions. In: FOCS, pp. 68–80 (1988)
Kearns, M.J., Li, M.: Learning in the presence of malicious errors. SIAM J. Comput. 22(4), 807–837 (1993)
MacKay, D.J.C.: Information Theory. Inference and Learning Algorithms. Cambridge University Press, New York (2002)
Mansour, Y., Rubinstein, A., Tennenholtz, M.: Robust probabilistic inference. In: Proceedings of the Twenty-Sixth Annual ACM-SIAM Symposium on Discrete Algorithms, SODA 2015, San Diego, CA, USA, January 4–6, 2015, pp. 449–460 (2015)
Mansour, Y., Rubinstein, A., Vardi, S., Xie, N.: Converting online algorithms to local computation algorithms. ICALP 1, 653–664 (2012)
Mansour, Y., Vardi, S.: A local computation approximation scheme to maximum matching. In: APPROX-RANDOM, pp. 260–273 (2013)
Mossel, E., O’Donnell, R., Oleszkiewicz, K.: Noise stability of functions with low influences invariance and optimality. In: FOCS, pp. 21–30 (2005)
Pearl, J.: Causality: Models, Reasoning, and Inference. Cambridge University Press, New York (2000)
Rubinfeld, R., Tamir, G., Vardi, S., Xie, N.: Fast local computation algorithms. In: ICS, pp. 223–238 (2011)
Valiant, L.G.: Learning disjunction of conjunctions. In: Proceedings of the 9th International Joint Conference on Artificial Intelligence - Volume 1, IJCAI 1985, pp. 560–566 (1985)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Mansour, Y. (2015). Robust Inference and Local Algorithms. In: Italiano, G., Pighizzini, G., Sannella, D. (eds) Mathematical Foundations of Computer Science 2015. MFCS 2015. Lecture Notes in Computer Science(), vol 9234. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-662-48057-1_4
Download citation
DOI: https://doi.org/10.1007/978-3-662-48057-1_4
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-662-48056-4
Online ISBN: 978-3-662-48057-1
eBook Packages: Computer ScienceComputer Science (R0)