Abstract
We address a fundamental problem of complexity theory – the inadequacy of worst-case complexity for the task of evaluating the computational resources required for real life problems. While being the best known measure and enjoying the support of a rich and elegant theory, worst-case complexity seems gives rise to over-pessimistic complexity values. Many standard task, that are being carried out routinely in machine learning applications, are NP-hard, that is, infeasible from the worst-case-complexity perspective. In this work we offer an alternative measure of complexity for approximations-optimization tasks. Our approach is to define a hierarchy on the set of inputs to a learning task, so that natural (’real data’) inputs occupy only bounded levels of this hierarchy and that there are algorithms that handle in polynomial time each such bounded level.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Levin, L.A.: Robust measures of information. Comput. J. 42, 284–286 (1999)
Ben-David, S., Chor, B., Goldreich, O., Luby, M.: On the theory of average case complexity. J. Comput. Syst. Sci. 44, 193–219 (1992)
Fellows, M.R.: Parameterized complexity: The main ideas and connections to practical computing. Electr. Notes Theor. Comput. Sci. 61 (2002)
Spielman, D.A., Teng, S.H.: Smoothed analysis of algorithms: Why the simplex algorithm usually takes polynomial time. J. ACM 51, 385–463 (2004)
Ben-David, S., Eiron, N., Long, P.M.: On the difficulty of approximately maximizing agreements. J. Comput. Syst. Sci. 66, 496–514 (2003)
Ben-David, S., Eiron, N., Simon, H.U.: The computational complexity of densest region detection. J. Comput. Syst. Sci. 64, 22–47 (2002)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ben-David, S. (2006). Alternative Measures of Computational Complexity with Applications to Agnostic Learning. In: Cai, JY., Cooper, S.B., Li, A. (eds) Theory and Applications of Models of Computation. TAMC 2006. Lecture Notes in Computer Science, vol 3959. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11750321_22
Download citation
DOI: https://doi.org/10.1007/11750321_22
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-34021-8
Online ISBN: 978-3-540-34022-5
eBook Packages: Computer ScienceComputer Science (R0)