Displaying similar documents to “A scaling result for explosive processes.”

An extended problem to Bertrand's paradox

Mostafa K. Ardakani, Shaun S. Wulff (2014)

Discussiones Mathematicae Probability and Statistics

Similarity:

Bertrand's paradox is a longstanding problem within the classical interpretation of probability theory. The solutions 1/2, 1/3, and 1/4 were proposed using three different approaches to model the problem. In this article, an extended problem, of which Bertrand's paradox is a special case, is proposed and solved. For the special case, it is shown that the corresponding solution is 1/3. Moreover, the reasons of inconsistency are discussed and a proper modeling approach is determined by...

Random split of the interval [0,1]

B. Kopociński (2004)

Applicationes Mathematicae

Similarity:

We define two splitting procedures of the interval [0,1], one using uniformly distributed points on the chosen piece and the other splitting a piece in half. We also define two procedures for choosing the piece to be split; one chooses a piece with a probability proportional to its length and the other chooses each piece with equal probability. We analyse the probability distribution of the lengths of the pieces arising from these procedures.

Probabilities of discrepancy between minima of cross-validation, Vapnik bounds and true risks

Przemysław Klęsk (2010)

International Journal of Applied Mathematics and Computer Science

Similarity:

Two known approaches to complexity selection are taken under consideration: n-fold cross-validation and structural risk minimization. Obviously, in either approach, a discrepancy between the indicated optimal complexity (indicated as the minimum of a generalization error estimate or a bound) and the genuine minimum of unknown true risks is possible. In the paper, this problem is posed in a novel quantitative way. We state and prove theorems demonstrating how one can calculate pessimistic...

Large deviations for independent random variables – Application to Erdös-Renyi’s functional law of large numbers

Jamal Najim (2005)

ESAIM: Probability and Statistics

Similarity:

A Large Deviation Principle (LDP) is proved for the family 1 n ∑ 1 n 𝐟 ( x i n ) · Z i n where the deterministic probability measure 1 n ∑ 1 n δ x i n converges weakly to a probability measure R and ( Z i n ) i ∈ ℕ are ℝ d -valued independent random variables whose distribution depends on x i n and satisfies the following exponential moments condition: sup i , n 𝔼 e α * | Z i n | < + ∞ forsome 0 < α * < + ∞ . In this context, the identification of the rate function is non-trivial due to the absence of equidistribution. We rely on fine convex analysis to address this issue. Among...