Skip to main content
SpringerLink
Log in

On the MDM Method for Solving the General Quadratic Problem of Mathematical Diagnostics

  • MATHEMATICS
  • Published:
Vestnik St. Petersburg University, Mathematics Aims and scope Submit manuscript

Abstract

The term “mathematical diagnostics” was introduced by V. F. Demyanov in the early 2000s. The simplest problem of mathematical diagnostics is to determine the relative position of some point p and the convex hull C of a finite number of given points in n-dimensional Euclidean space. Of interest is the answer to the following questions: does the point p belong to the set C or not? If p does not belong to C, then what is the distance from p to C? In the general problem of mathematical diagnostics, two convex hulls are considered. The question is whether they have common points. If there are no common points, then it is required to find the distance between these hulls. From an algorithmic point of view, the problems of mathematical diagnostics reduce to special linear- or quadratic-programming problems, which can be solved by finite methods. However, the implementation of this approach in the case of large data arrays runs into serious computational difficulties. Such situations can be dealt with by infinite but easily implemented methods, which allow one to obtain an approximate solution with the required accuracy in a finite number of iterations. These methods include the MDM method. It was developed by Mitchell, Demyanov, and Malozemov in 1971 for other purposes, but later found application in machine learning. From a modern point of view, the original version of the MDM method can be used to solve only the simplest problems of mathematical diagnostics. This article gives a natural generalization of the MDM method, oriented towards solving general problems of mathematical diagnostics. In addition, it is shown how, using the generalized MDM method, a solution to the problem of the linear separation of two finite sets, in which the separating strip has the largest width, is found.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

REFERENCES

  1. B. F. Mitchell, V. F. Dem’yanov, and V. N. Malozemov, “Finding the point of a polyhedron closest to the origin,” SIAM J. Control 12, 19–26 (1974).

    Article  MathSciNet  MATH  Google Scholar 

  2. A. Barbero, J. Lopez, and J. R. Dorronsoro, “An accelerated MDM algorithm for SVM training,” in Proc. 16th European Symp. on Artificial Neural Networks — Advances in Computational Intelligence and Learning, Bruges, Belgium, Apr. 23–25, 2008, pp. 421–426.

  3. J. Lopez, On the Relationship Among the MDM, SMO and SVM-Light Algorithms for Training Support Vector Machines, Master’s Thesis (Univ. Autonoma de Madrid, Madrid, 2008).

  4. J. Lopez, A. Barbero, and J. R. Dorronsoro, “On the equivalence of the SMO and MDM algorithms for SVM training,” in Machine Learning and Knowledge Discovery in Databases: Proc. European Conf., Antwerp, Belgium, Sept. 15–19, 2008, Ed. by W. Daelemans, et al. (Springer-Verlag, Berlin, 2008), Vol. 1, pp. 288–300.

  5. J. Lopez and J. R. Dorronsoro, “Common framework for the convergence of the GSK, MDM and SMO algorithms,” in Artificial Neural Networks — ICANN 2010, Proc. 20th Int. Conf., Thessaloniki, Greece, Sept. 15–18, 2020, Ed. by K. Diamantaras, W. Duch, and L. S. Iliadis (Springer-Verlag, Berlin, 2010), Vol. 2, pp. 82–87.

  6. J. Lopez and J. R. Dorronsoro, “Linear convergence rate for the MDM algorithm for the nearest point problem,” Pattern Recognit. 48, 1510–1522 (2015).

    Article  MATH  Google Scholar 

  7. M. Zeng, Y. Yang, and J. Cheng, “A generalized Mitchell–Dem’yanov–Malozemov algorithm for one-class support vector machine,” Knowl.-Based Syst. 109, 17–24 (2016).

    Article  Google Scholar 

  8. M. P. Deisenroth, A. A. Faisal, and C. S. Ong, Mathematics for Machine Learning (Cambridge Univ. Press, Cambridge, 2020). https://mml-book.com.

    Book  MATH  Google Scholar 

  9. J. C. Platt, Sequential Minimal Optimization: A Fast Algorithm for Training Support Vector Machines, Technical Report No. MSR-TR-98-14 (1998).

  10. J. Lopez and J. R. Dorronsoro, “A simple proof of the convergence of the SMO algorithm for linearly separable problems,” in Artificial Neural Networks — ICANN 2009: Proc. 19th Int. Conf., Limassol, Cyprus, Sept. 14–17, 2009 (Springer-Verlag, Berlin, 2009), Vol. 1, pp. 904–912.

  11. J. L. Lazaro, Analysis and Convergence of SMO-like Decomposition and Geometrical Algorithms for Support Vector Machines, PhD Thesis (Univ. Autonoma de Madrid, Madrid, 2011).

Download references

Author information

Authors and Affiliations

  1. St. Petersburg State University, 199034, St. Petersburg, Russia

    V. N. Malozemov

  2. St. Petersburg State University of Economics, 191023, St. Petersburg, Russia

    N. A. Solovyeva

Authors
  1. V. N. Malozemov
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. N. A. Solovyeva
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to V. N. Malozemov or N. A. Solovyeva.

Ethics declarations

The authors declare that they have no conflicts of interest.

Additional information

Translated by E. Chernokozhin

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Malozemov, V.N., Solovyeva, N.A. On the MDM Method for Solving the General Quadratic Problem of Mathematical Diagnostics. Vestnik St.Petersb. Univ.Math. 56, 362–372 (2023). https://doi.org/10.1134/S106345412303007X

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1134/S106345412303007X

Keywords:

Search

Navigation