Golomb–Dickman constant

From HandWiki

In mathematics, the Golomb–Dickman constant arises in the theory of random permutations and in number theory. Its value is

λ=0.62432998854355087099293638310083724 (sequence A084945 in the OEIS)

It is not known whether this constant is rational or irrational.[1]

Definitions

Let an be the average — taken over all permutations of a set of size n — of the length of the longest cycle in each permutation. Then the Golomb–Dickman constant is

λ=limnann.

In the language of probability theory, λn is asymptotically the expected length of the longest cycle in a uniformly distributed random permutation of a set of size n.

In number theory, the Golomb–Dickman constant appears in connection with the average size of the largest prime factor of an integer. More precisely,

λ=limn1nk=2nlog(P1(k))log(k),

where P1(k) is the largest prime factor of k (sequence A006530 in the OEIS) . So if k is a d digit integer, then λd is the asymptotic average number of digits of the largest prime factor of k.

The Golomb–Dickman constant appears in number theory in a different way. What is the probability that second largest prime factor of n is smaller than the square root of the largest prime factor of n? Asymptotically, this probability is λ. More precisely,

λ=limnProb{P2(n)P1(n)}

where P2(n) is the second largest prime factor n.

The Golomb-Dickman constant also arises when we consider the average length of the largest cycle of any function from a finite set to itself. If X is a finite set, if we repeatedly apply a function f: XX to any element x of this set, it eventually enters a cycle, meaning that for some k we have fn+k(x)=fn(x) for sufficiently large n; the smallest k with this property is the length of the cycle. Let bn be the average, taken over all functions from a set of size n to itself, of the length of the largest cycle. Then Purdom and Williams[2] proved that

limnbnn=π2λ.

Formulae

There are several expressions for λ. These include:

λ=01eLi(t)dt

where Li(t) is the logarithmic integral,

λ=0etE1(t)dt

where E1(t) is the exponential integral, and

λ=0ρ(t)t+2dt

and

λ=0ρ(t)(t+1)2dt

where ρ(t) is the Dickman function.

See also

References

  1. Lagarias, Jeffrey (2013). "Euler's constant: Euler's work and modern developments". Bull. Amer. Math. Soc. 50 (4): 527–628. doi:10.1090/S0273-0979-2013-01423-X. Bibcode2013arXiv1303.1856L. 
  2. Purdon, P.; Williams, J.H (1968). "Cycle length in a random function". Trans. Amer. Math. Soc. 133 (2): 547–551. doi:10.1090/S0002-9947-1968-0228032-3.