Utilizing Geometric Anomalies of High Dimension: When Complexity Makes Computation Easier

@inproceedings{Kainen1997UtilizingGA,
  title={Utilizing Geometric Anomalies of High Dimension: When Complexity Makes Computation Easier},
  author={P. C. Kainen},
  year={1997}
}
  • P. C. Kainen
  • Published 1997
  • Mathematics
  • Just as a busy kitchen can be more efficient than an idle one, Kleinrock showed 35 years ago that heavily used networks admit simple heuristic approximations with excellent quantitative accuracy. We describe a number of different examples in which having many parameters actually facilitates computation and we suggest connections with geometric phenomena in high-dimensional spaces. It seems that in several interesting and quite general situations, dimensionality may be a blessing in disguise… CONTINUE READING
    22 Citations
    Bringing the Blessing of Dimensionality to the Edge
    • 1
    • PDF
    Blessing of dimensionality: mathematical foundations of the statistical physics of data
    • Alexander N. Gorban, I. Tyukin
    • Computer Science, Medicine
    • Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences
    • 2018
    • 48
    • PDF
    General stochastic separation theorems with optimal bounds
    • PDF
    Blessing of dimensionality at the edge
    • 1
    • PDF
    The unreasonable effectiveness of small neural ensembles in high-dimensional brain
    • 24
    • PDF
    Kernel Stochastic Separation Theorems and Separability Characterizations of Kernel Classifiers
    • 1

    References

    SHOWING 1-10 OF 22 REFERENCES
    Worst-Case Performance Bounds for Simple One-Dimensional Packing Algorithms
    • 827
    • PDF
    Sphere Packings, Lattices and Groups
    • 3,317
    • PDF
    Expected Wire Length between Two Randomly Chosen Terminals
    • 11
    A geometric method to obtain error-correcting classification by neural networks with fewer hidden units
    • 3
    Universal approximation bounds for superpositions of a sigmoidal function
    • A. Barron
    • Mathematics, Computer Science
    • IEEE Trans. Inf. Theory
    • 1993
    • 2,322
    • PDF
    Ten lectures on the probabilistic method
    • 479