Results 221 to 230 of about 19,121 (268)

Improving sampling efficacy on high-dimensional distributions with thin high-density regions using Conservative Hamiltonian Monte Carlo. [PDF]

PNAS Nexus
McGregor G, Wan ATS.
europepmc   +1 more source

Tests for Categorical Data Beyond Pearson: A Distance Covariance and Energy Distance Approach. [PDF]

Biom J
Castro-Prado F, González-Manteiga W, Costas J, Facal F, Edelmann D.   +4 more
europepmc   +1 more source

Some of the next articles are maybe not open access.

Related searches:

Discrete Approximations of Probability Distributions

Management Science, 1983
Practical limits on the size of most probabilistic models require that probability distributions be approximated by a few representative values and associated probabilities. This paper demonstrates that methods commonly used to determine discrete approximations of probability distributions systematically underestimate the moments of the original ...
Allen C. Miller, III, Thomas R. Rice
exaly   +3 more sources

Approximation by Discrete GB-Splines

Numerical Algorithms, 2001
Discrete generalized splines are continuous piecewise defined functions which meet some smoothness conditions for the first and second divided difference at the knots. They are a generalization both of smooth generalized splines and classic discrete cubic splines. The paper is devoted to the study of generalized splines.
openaire   +2 more sources

Approximating discrete probability distributions

IEEE Transactions on Information Theory, 1969
The method of minimum discrimination information estimation is applied to the problem of estimating an n -dimensional discrete probability distribution in terms of lower order marginal distributions. The procedure provides a convergent iterative algorithm. The method yields regular best asymptotically normal (RBAN) estimates.
Harry H. Ku, Solomon Kullback
openaire   +2 more sources

Approximation by discrete hermite interpolation

2010 11th International Conference on Control Automation Robotics & Vision, 2010
For a function f(t) defined on the discrete interval N[a, b + 2] = {a, a + 1, …, 6 + 2}, we develop a class of quintic discrete Hermite interpolate H ρ f(t) that involves only differences. Further, explicit error bounds are offered in the form of the inequality ||f-H ρ f||≤c j max/t∊N[a, b+2-j] | Δj f(t)|, 2≤j≤6 where the constants C j , 2 ≤ 6 are ...
Fengmin Chen, Patricia J. Y. Wong
openaire   +1 more source

Discrete analogues of Laplace's approximation

Asymptotic Analysis, 2007
An asymptotic formula is derived for the sum I n (1|q):=Σ n k=0 f n (k)q g n (k)
Wang, X.S., Wong, R.
openaire   +2 more sources

Discrete approximation of the Koch curve

Computers & Graphics, 1993
Abstract Existing algorithms for Koch curve generation do not consider the discrete environment of the computer. They do not define the termination condition explicitly. Therefore, generation of the curve must be terminated in ad-hoc manners. This paper describes a new algorithm for discretely approximated Koch curve generation which produces only ...
Sam Chung Hwang, Hyun Seung Yang
openaire   +1 more source

Approximation by discrete spline interpolation

2010 11th International Conference on Control Automation Robotics & Vision, 2010
For a function f(t) defined on the discrete interval N[a, b + 2] = {a, a + 1, …, b + 2}, we develop a class of quintic discrete spline interpolate S ρ f(t) that involves only differences. Further, explicit error bounds are offered in the form of the inequality ||f-H ρ f||≤d j max/t∊N[a, b+2-j] |Δj f(t)|, 2≤j≤6 where the constants d j , 2 ≤ j ≤ 6 are
Fengmin Chen, Patricia J. Y. Wong
openaire   +1 more source

Discrete Nonlinear Mean Approximation

ZAMM - Journal of Applied Mathematics and Mechanics / Zeitschrift für Angewandte Mathematik und Mechanik, 1977
AbstractBest approximation on a finite set by a non‐linear family of functions with respect to a general sum “norm”, which includes as a special case the Lp norms (1 < p < ∞), is considered. Properties of best approximations are given. It is shown that a local minimum of the error may not be a global minimum. Computation of best approximations is
openaire   +2 more sources