On learning mixtures of heavy-tailed distributions

@article{Dasgupta2005OnLM,
  title={On learning mixtures of heavy-tailed distributions},
  author={Anirban Dasgupta and John E. Hopcroft and Jon M. Kleinberg and Mark Sandler},
  journal={46th Annual IEEE Symposium on Foundations of Computer Science (FOCS'05)},
  year={2005},
  pages={491-500}
}
We consider the problem of learning mixtures of arbitrary symmetric distributions. We formulate sufficient separation conditions and present a learning algorithm with provable guarantees for mixtures of distributions that satisfy these separation conditions. Our bounds are independent of the variances of the distributions; to the best of our knowledge, there were no previous algorithms known with provable learning guarantees for distributions having infinite variance and/or expectation. For… CONTINUE READING
Highly Cited
This paper has 49 citations. REVIEW CITATIONS

From This Paper

Topics from this paper.
36 Citations
16 References
Similar Papers

References

Publications referenced by this paper.
Showing 1-10 of 16 references

Statistical data analysis based on the L1 norm and related methods

  • Y. Dodge, editor
  • Elsevier Science Publishers B.V.,
  • 2002
1 Excerpt

Kannan . Learningmixtures of arbitrary gaussians

  • A. Fiat Y. Azar, A. Karlin, F. McSherry, J. Saia
  • 2001

Similar Papers

Loading similar papers…