Corpus ID: 208527072

On the optimality of kernels for high-dimensional clustering

@article{Vankadara2019OnTO,
  title={On the optimality of kernels for high-dimensional clustering},
  author={Leena Chennuru Vankadara and Debarghya Ghoshdastidar},
  journal={ArXiv},
  year={2019},
  volume={abs/1912.00458}
}
  • Leena Chennuru Vankadara, Debarghya Ghoshdastidar
  • Published in ArXiv 2019
  • Mathematics, Computer Science
  • This paper studies the optimality of kernel methods in high-dimensional data clustering. Recent works have studied the large sample performance of kernel clustering in the high-dimensional regime, where Euclidean distance becomes less informative. However, it is unknown whether popular methods, such as kernel k-means, are optimal in this regime. We consider the problem of high-dimensional Gaussian clustering and show that, with the exponential kernel function, the sufficient conditions for… CONTINUE READING

    Create an AI-powered research feed to stay up to date with new papers like this posted to ArXiv

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 14 REFERENCES

    NP-hardness of Euclidean sum-of-squares clustering

    VIEW 3 EXCERPTS
    HIGHLY INFLUENTIAL

    Exponential Error Rates of SDP for Block Models: Beyond Grothendieck’s Inequality

    Useful concentration results Proposition 5 (Bernstein’s inequality (Vershynin, 2018))

    • C ‖X1‖2ψ
    • 2018

    A Constant-Factor Approximation Algorithm for Co-clustering

    VIEW 1 EXCERPT