Empirical Bernstein stopping

@inproceedings{Mnih2008EmpiricalBS,
  title={Empirical Bernstein stopping},
  author={Volodymyr Mnih and Csaba Szepesv{\'a}ri and Jean-Yves Audibert},
  booktitle={ICML},
  year={2008}
}
Sampling is a popular way of scaling up machine learning algorithms to large datasets. The question often is how many samples are needed. Adaptive stopping algorithms monitor the performance in an online fashion and they can stop early, saving valuable resources. We consider problems where probabilistic guarantees are desired and demonstrate how recently-introduced empirical Bernstein bounds can be used to design stopping rules that are efficient. We provide upper bounds on the sample… CONTINUE READING
Highly Cited
This paper has 173 citations. REVIEW CITATIONS

Topics

Statistics

02040'07'08'09'10'11'12'13'14'15'16'17'18
Citations per Year

174 Citations

Semantic Scholar estimates that this publication has 174 citations based on the available data.

See our FAQ for additional information.