Adaptive Overrelaxed Bound Optimization Methods

  title={Adaptive Overrelaxed Bound Optimization Methods},
  author={Ruslan Salakhutdinov and Sam T. Roweis},
We study a class ofoverrelaxedbound optimization algorithms, and their relationship to standard bound optimizers, such as ExpectationMaximization, Iterative Scaling, CCCP and Non-Negative Matrix Factorization. We provide a theoretical analysis of the convergence properties of these optimizers and identify analytic conditions under which they are expected to outperform the standard versions. Based on this analysis, we propose a novel, simple adaptive overrelaxed scheme for practical optimization… CONTINUE READING
Highly Influential
This paper has highly influenced 10 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 127 citations. REVIEW CITATIONS


Publications citing this paper.
Showing 1-10 of 67 extracted citations

127 Citations

Citations per Year
Semantic Scholar estimates that this publication has 127 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-10 of 20 references

Algorithms for maximum-likelihood logistic regression

  • Tom Minka
  • Technical Report 758,
  • 2001
1 Excerpt

The convexconcave computational procedure ( CCCP )

  • Alan Yuille, Anand Rangarajan
  • Advances in Neural Information Processing Systems
  • 2000

Hinton . SMEM algorithm for mixture models

  • Naonori Ueda, Ryohei Nakano, Zoubin Ghabramani, E. Geoffrey
  • Neural Computation
  • 1999

EM algorthms for PCA and SPCA

  • S. T. Roweis
  • Advances in neural information processing systems
  • 1998
1 Excerpt

Similar Papers

Loading similar papers…