Local Rademacher Complexities

@inproceedings{Bartlett2002LocalRC,
  title={Local Rademacher Complexities},
  author={P. L. Bartlett and Olivier Bousquet and Shahar Mendelson},
  year={2002}
}
We propose new bounds on the error of learning algorithms in terms of a data-dependent notion of complexity. The estimates we establish give optimal rates and are based on a local and empirical version of Rademacher averages, in the sense that the Rademacher averages are computed from the data, on a subset of functions with small empirical error. We present some applications to classification and prediction with convex function classes, and with kernel classes in particular. 
Highly Influential
This paper has highly influenced 58 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 353 citations. REVIEW CITATIONS

From This Paper

Topics from this paper.
217 Citations
40 References
Similar Papers

Citations

Publications citing this paper.
Showing 1-10 of 217 extracted citations

353 Citations

02040'05'08'11'14'17
Citations per Year
Semantic Scholar estimates that this publication has 353 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.
Showing 1-10 of 40 references

1991).Probability in Banach Spaces: Isoperimetry and Processes

  • M. LEDOUX, M. TALAGRAND
  • 1991
Highly Influential
5 Excerpts

S

  • VAN DE GEER
  • 2000
Highly Influential
4 Excerpts

Similar Papers

Loading similar papers…