Corpus ID: 204960893

Balancing Gaussian vectors in high dimension

@article{Meka2020BalancingGV,
  title={Balancing Gaussian vectors in high dimension},
  author={Raghu Meka and Philippe Rigollet and Paxton Turner},
  journal={ArXiv},
  year={2020},
  volume={abs/1910.13972}
}
  • Raghu Meka, Philippe Rigollet, Paxton Turner
  • Published 2020
  • Computer Science, Mathematics
  • ArXiv
  • Motivated by problems in controlled experiments, we study the discrepancy of random matrices with continuous entries where the number of columns $n$ is much larger than the number of rows $m$. Our first result shows that if $\omega(1) \leq m \leq o(n)$, a matrix with i.i.d. standard Gaussian entries has discrepancy $\Theta(\sqrt{n} \, 2^{-n/m})$ with high probability. This provides sharp guarantees for Gaussian discrepancy in a regime that had not been considered before in the existing… CONTINUE READING

    Figures and Topics from this paper.

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 43 REFERENCES

    "Integer-making" theorems

    Asymptotic Aanlysis, volume 48

    • J. D. Murray
    • 1984

    Asymptotic theory of rerandomization in treatment–control experiments

    Constructive Algorithms for Discrepancy Minimization

    • Nikhil Bansal
    • Mathematics, Computer Science
    • 2010 IEEE 51st Annual Symposium on Foundations of Computer Science
    • 2010

    Constructive Discrepancy Minimization for Convex Sets

    • Thomas Rothvoss
    • Mathematics, Computer Science
    • 2014 IEEE 55th Annual Symposium on Foundations of Computer Science
    • 2014