Information complexity of black-box convex optimization: A new look via feedback information theory

@article{Raginsky2009InformationCO,
  title={Information complexity of black-box convex optimization: A new look via feedback information theory},
  author={Maxim Raginsky and Alexander Rakhlin},
  journal={2009 47th Annual Allerton Conference on Communication, Control, and Computing (Allerton)},
  year={2009},
  pages={803-510}
}
This paper revisits information complexity of black-box convex optimization, first studied in the seminal work of Nemirovski and Yudin, from the perspective of feedback information theory. These days, large-scale convex programming arises in a variety of applications, and it is important to refine our understanding of its fundamental limitations. The goal of black-box convex optimization is to minimize an unknown convex objective function from a given class over a compact, convex domain using… CONTINUE READING

References

Publications referenced by this paper.
Showing 1-7 of 7 references

Minimax Bounds for Active Learning

IEEE Transactions on Information Theory • 2008
View 4 Excerpts
Highly Influenced

Problem Complexity and Method Efficiency in Optimization

A. S. Nemirovski, D. B. Yudin
1983
View 10 Excerpts
Highly Influenced

Generalizing the Fano inequality

IEEE Trans. Information Theory • 1994
View 1 Excerpt

Similar Papers

Loading similar papers…