Cybernetics And Systems Analysis logo
Editorial Board Announcements Abstracts Authors Archive
Cybernetics And Systems Analysis
International Theoretical Science Journal
-->

UDC 004.8
M.I. Schlesinger1, E.V. Vodolazskiy2


1 International Research and Training Center for Information Technologies and Systems of the NAS of Ukraine and MES of Ukraine, Kyiv, Ukraine

schles@irtc.org.ua

2 International Research and Training Center for Information Technologies and Systems of the NAS of Ukraine and MES of Ukraine, Kyiv, Ukraine

waterlaz@gmail.com

MINIMAX DEVIATION STRATEGIES FOR MACHINE LEARNING
AND RECOGNITION WITH SHORT LEARNING SAMPLES

Abstract. The article analyses risk-oriented formulation of pattern recognition and machine learning problems. Based on arguments from multicriteria optimization, a class of improper strategies is defined that are dominated by some other strategy. A general form of strategies that are not improper is derived. It is shown that some widely used approaches are improper in the defined sense, including the maximum likelihood estimation approach. This drawback is especially apparent when dealing with short learning samples of fixed length. A unified formulation of pattern recognition and machine learning problems is presented that embraces the whole range of sizes of the learning sample, including zero size. It is proven that solutions to problems in the presented formulation are not improper. The concept of minimax deviation recognition and learning is formulated, several examples of its implementation are presented and compared with the widely used methods based on the maximal likelihood estimation.

Keywords: pattern recognition, machine learning, short learning sample.


FULL TEXT

REFERENCES

  1. Robbins H. Asymptotically subminimax solutions of compound statistical decision problems. Proc. the Second Berkeley Symposium on Mathematical Statistics and Probability (31 July – 12 August 1950, Berkeley, USA). Berkeley, 1950. P. 131–148.

  2. Duda R.O., Hart P.E., Stork D.G. Pattern classification. New York: Wiley, 2000. 688 p.

  3. Webb A.R. Statistical pattern recognition. Wiley, 2002. 514 p.

  4. Borwein J.M., Lewis A.S. Convex analysis and nonlinear optimization. New York: Springer Verlag, 2000. XII, 310 p.

  5. Boyd S., Vandenberghe L. Convex optimization. New York: Cambrige University Press, 2004. 730 p.

  6. Hiriart-Urruty J.-B., Lemarchal C. Fundamentals of convex analysis. Berlin; Heidelberg: Springer Verlag, 2002. 269 p.

  7. Shor N.Z. Nondifferentiable optimization and polynomial problems. Springer, 1998. 413 p.




© 2022 Kibernetika.org. All rights reserved.