Latin Hypercube Sampling

By R. Iman. 2006

617 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/558edf219dedcdd00ff47105c4c8ff2fd5925198

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Statistics and Probability

Citations in the corpus

Gaussian process regression for forecasting battery state of health (2017, result): “However, this was not an issue in the present study, as was veriﬁed by repeated diverse ini-tialisations using Latin hypercube sampling [21] yielding identical results.”
High-Order Collocation Methods for Differential Equations with Random Inputs (2005, methodology): “To accelerate convergence, several techniques have been developed, for example, Latin hypercube sampling, [34, 48], the quasi-Monte Carlo (QMC) method, [14, 39, 40], and the Markov chain Monte Carlo method (MCMC) [16, 22, 36].”
Probabilistic Load Flow Evaluation With Hybrid Latin Hypercube Sampling and Cholesky Decomposition (2009, background): “As value of the former is always larger than the latter for any , LHS is expected to provide better probabilistic input space coverage than SRS [27].”
Polynomial chaos for the approximation of uncertainties: Chances and limits (2008, methodology): “In Section 2.1 we will give a short introduction to the theory of polynomial chaos, which can be an alternative method to Monte Carlo and its improved versions, such as Latin Hypercube Sampling [26], Quasi-Monte Carlo Method [8], Markov Chain Monte Carlo Method [31] and importance sampling [33].”
A randomized orthogonal array-based procedure for the estimation of first- and second-order Sobol' indices (2015, positive): “We derive theoretical results in the particular case of ﬁrst-order SIs from the work by Janon et al. [19] on asymptotical properties of SIs and from the work by Loh [37] on asymptotical properties of LHS.”
Multiresponse multilayer vadose zone model calibration using Markov chain Monte Carlo simulation and field water retention data (2011, methodology): “The initial sample in AMALGAM was generated using Latin hypercube sampling [e.g., Iman, 1999] with the following lower and upper bounds of the various parameters: s ¼ 0:3 0:7 m3 m 3; ¼ 1 20 m 1; n ¼ 1.1 9.0 [ ]; Ks ¼ 10 7 10 3 m s 1; l ¼ 3.0 3.0 [ ].”
Fast Numerical Methods for Stochastic Computations: A Review (2009, neutral): “[50, 74]), quasi Monte Carlo (cf.”
Deep UQ: Learning deep neural network surrogate models for high dimensional uncertainty quantification (2018, methodology): “2: Use Latin Hypercube sampling (LHS) [67] to generate ninit samples of λ within the bounding box B.”