The alpha-EM algorithm: surrogate likelihood maximization using alpha-logarithmic information measures

@article{Matsuyama2003TheAA,
  title={The alpha-EM algorithm: surrogate likelihood maximization using alpha-logarithmic information measures},
  author={Yasuo Matsuyama},
  journal={IEEE Trans. Information Theory},
  year={2003},
  volume={49},
  pages={692-706}
}
A new likelihood maximization algorithm called the -EM algorithm ( -Expectation–Maximization algorithm) is presented. This algorithm outperforms the traditional or logarithmic EM algorithm in terms of convergence speed for an appropriate range of the design parameter . The log-EM algorithm is a special case corresponding to = 1. The main idea behind the -EM algorithm is to search for an effective surrogate function or a minorizer for the maximization of the observed data’s likelihood ratio. The… CONTINUE READING
30 Citations
33 References
Similar Papers

Citations

Publications citing this paper.
Showing 1-10 of 30 extracted citations

References

Publications referenced by this paper.
Showing 1-10 of 33 references

The ECME algorithm: A simple extension of EM and ECM with faster monotone convergence

  • C. Liu, D. B. Rubin
  • Biometrika, vol. 81, pp. 633–648, 1994.
  • 1994
Highly Influential
11 Excerpts

Information-type measures of difference of probability distributions and indirect observations

  • I. Csiszár
  • Studia Sci. Math. Hung. , vol. 2, pp. 299–318…
  • 1967
Highly Influential
6 Excerpts

Luenberger,Introduction to Linear and Nonlinear Programming

  • D G.
  • 1973
Highly Influential
4 Excerpts

Optimization transfer for computational learning: A hierarchy from f-ICA and alpha-EM to their offsprings

  • Y. Matsuyama, S. Imahara, N. Katsumata
  • inProc. Int. Joint Conf. Neural Networks , vol…
  • 2002
2 Excerpts

Supervised map ICA: Applications to brain functional MRI

  • Y. Matsuyama, R. Kawamura
  • inProc. Int. Conf. Neural Information Processing…
  • 2002
1 Excerpt

Optimization transfer using surrogate objective functions (with discussion)

  • K. Lange, D. R. Hunter, I. Yang
  • J. Comput. Graph. Statist. , vol. 9, pp. 1–59…
  • 2000
2 Excerpts

The -ICA algorithm

  • Y. Matsuyama, N. Katsumata, Y. Suzuki, S. Imahara
  • Proc. 2nd Int. Workshop Independent Component…
  • 2000
1 Excerpt

Similar Papers

Loading similar papers…