• Corpus ID: 251564567

The VC-dimension of a class of multiples of the primes, and a connection to AdaBoost

@inproceedings{Thomas2022TheVO,
  title={The VC-dimension of a class of multiples of the primes, and a connection to AdaBoost},
  author={Andrew M. Thomas},
  year={2022}
}
A BSTRACT . We discuss the VC-dimension of a class of multiples of integers and primes (equivalently indicator functions) and demonstrate connections to prime counting functions. Additionally, we prove limit theorems for the behavior of an empirical risk minimization rule as well as the weights assigned to the output hypothesis in AdaBoost for these “prime-identifying” indicator functions, when we sample m n i.i.d. points uniformly from the integers { 2, . . . , n } . 

References

SHOWING 1-7 OF 7 REFERENCES

Learning integer lattices

An efficient learning algorithm with an absolute mistake bound of $k + \lfloor k\log (n\sqrt k ) \rfloor $ is given, where n is the maximum component of any tuple seen, and it is shown that this bound is approximately a $\log \log n$ factor larger than the lower bound on the worst case number of mistakes given by the VC dimension of lattices.

An Introduction to the Theory of Numbers

  • E. T.
  • Mathematics
    Nature
  • 1946
THIS book must be welcomed most warmly into X the select class of Oxford books on pure mathematics which have reached a second edition. It obviously appeals to a large class of mathematical readers.

Understanding Machine Learning - From Theory to Algorithms

The aim of this textbook is to introduce machine learning, and the algorithmic paradigms it offers, in a principled way in an advanced undergraduate or beginning graduate course.

Boosting: Foundations and Algorithms

This book offers an accessible introduction and essential reference for an approach to machine learning that creates highly accurate prediction rules by combining many weak and inaccurate rules of thumb.

As the d j are distinct, so must the a i,j be. Therefore, we must have m i ≤ k − 1. Our final result gives a bound on the VC-dimension of H k and H ′ k

    Warmuth . “ Learning Integer Lattices ”

    • An Introduction to the Theory of Numbers
    • 2008