Corpus ID: 7860945

Sample complexity of population recovery

@article{Polyanskiy2017SampleCO,
  title={Sample complexity of population recovery},
  author={Yury Polyanskiy and Ananda Theertha Suresh and Yihong Wu},
  journal={ArXiv},
  year={2017},
  volume={abs/1702.05574}
}
  • Yury Polyanskiy, Ananda Theertha Suresh, Yihong Wu
  • Published 2017
  • Mathematics, Computer Science
  • ArXiv
  • The problem of population recovery refers to estimating a distribution based on incomplete or corrupted samples. Consider a random poll of sample size $n$ conducted on a population of individuals, where each pollee is asked to answer $d$ binary questions. We consider one of the two polling impediments: (a) in lossy population recovery, a pollee may skip each question with probability $\epsilon$; (b) in noisy population recovery, a pollee may lie on each question with probability $\epsilon… CONTINUE READING

    Figures and Topics from this paper.

    Paper Mentions

    Citations

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

    Extrapolating the profile of a finite population

    VIEW 2 EXCERPTS
    CITES BACKGROUND

    Beyond Trace Reconstruction: Population Recovery from the Deletion Channel

    Sharp bounds for population recovery

    VIEW 9 EXCERPTS
    CITES RESULTS & METHODS
    HIGHLY INFLUENCED

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 33 REFERENCES

    Population recovery and partial identification

    VIEW 3 EXCERPTS

    Noisy Population Recovery in Polynomial Time

    A Polynomial Time Algorithm for Lossy Population Recovery

    VIEW 7 EXCERPTS
    HIGHLY INFLUENTIAL

    Finding Heavy Hitters from Lossy or Noisy Data

    VIEW 6 EXCERPTS
    HIGHLY INFLUENTIAL

    On the learnability of discrete distributions

    VIEW 3 EXCERPTS

    Optimal mean-based algorithms for trace reconstruction

    VIEW 10 EXCERPTS
    HIGHLY INFLUENTIAL

    Sharp bounds for population recovery

    VIEW 2 EXCERPTS

    Learning mixtures of product distributions over discrete domains

    VIEW 3 EXCERPTS