Lower Bounds for the Empirical Minimization Algorithm

  title={Lower Bounds for the Empirical Minimization Algorithm},
  author={Shahar Mendelson},
  journal={IEEE Transactions on Information Theory},
In this correspondence, we present a simple argument that proves that under mild geometric assumptions on the class F and the set of target functions T, the empirical minimization algorithm cannot yield a uniform error rate that is faster than 1/radic(k) in the function learning setup. This result holds for various loss functionals and the target functions from T that cause the slow uniform error rate are clearly exhibited. 
Highly Cited
This paper has 34 citations. REVIEW CITATIONS

From This Paper

Figures, tables, and topics from this paper.


Publications referenced by this paper.
Showing 1-10 of 19 references

Empirical minimization

  • P. L. Bartlett, S. Mendelson
  • Probability Theory and Related Fields, 135, 311…
  • 2006
1 Excerpt

Concentration Inequalities and Empirical Processes Theory Applied to the Analysis of Learning Algorithms

  • O. Bousquet
  • PhD thesis
  • 2002
1 Excerpt

Similar Papers

Loading similar papers…