Corpus ID: 12695525

On Communication Cost of Distributed Statistical Estimation and Dimensionality

@inproceedings{Garg2014OnCC,
  title={On Communication Cost of Distributed Statistical Estimation and Dimensionality},
  author={Ankit Garg and Tengyu Ma and Huy L. Nguyen},
  booktitle={NIPS},
  year={2014}
}
  • Ankit Garg, Tengyu Ma, Huy L. Nguyen
  • Published in NIPS 2014
  • Computer Science, Mathematics
  • We explore the connection between dimensionality and communication cost in distributed learning problems. Specifically we study the problem of estimating the mean θ→ of an unknown d dimensional gaussian distribution in the distributed setting. In this problem, the samples from the unknown distribution are distributed among m different machines. The goal is to estimate the mean θ→ at the optimal minimax rate while communicating as few bits as possible. We show that in this setting, the… CONTINUE READING

    Topics from this paper.

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 47 CITATIONS

    Learning Distributions from their Samples under Communication Constraints

    VIEW 6 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    FILTER CITATIONS BY YEAR

    2015
    2020

    CITATION STATISTICS

    • 6 Highly Influenced Citations

    • Averaged 10 Citations per year from 2018 through 2020

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 23 REFERENCES

    Communication-efficient algorithms for statistical optimization

    Information Equals Amortized Communication

    VIEW 2 EXCERPTS

    A Tight Bound for Set Disjointness in the Message-Passing Model

    VIEW 2 EXCERPTS

    Informational complexity and the direct sum problem for simultaneous message complexity

    VIEW 1 EXCERPT