Results 11 to 20 of about 992,707 (136)
Tree Ensemble Explainability through the Hoeffding Functional Decomposition and TreeHFD Algorithm
arXiv.orgTree ensembles have demonstrated state-of-the-art predictive performance across a wide range of problems involving tabular data. Nevertheless, the black-box nature of tree ensembles is a strong limitation, especially for applications with critical ...
Cl'ement B'enard
semanticscholar +3 more sources
Moment inequalities for sums of weakly dependent random fields [PDF]
Bernoulli, 2023 We derive both Azuma-Hoeffding and Burkholder-type inequalities for partial sums over a rectangular grid of dimension $d$ of a random field satisfying a weak dependency assumption of projective type: the difference between the expectation of an element ...
G. Blanchard +2 more
semanticscholar +1 more source
On variance estimation of random forests with Infinite-order U-statistics [PDF]
Electronic Journal of Statistics, 2022 Infinite-order U-statistics (IOUS) has been used extensively on subbagging ensemble learning algorithms such as random forests to quantify its uncertainty.
Tianning Xu, Ruoqing Zhu, Xiaofeng Shao
semanticscholar +1 more source
Tail inference using extreme U-statistics [PDF]
Electronic Journal of Statistics, 2022 Extreme U-statistics arise when the kernel of a U-statistic has a high degree but depends only on its arguments through a small number of top order statistics.
Jochem Oorschot, J. Segers, Chen Zhou
semanticscholar +1 more source
Hoeffding decomposition of black-box models with dependent inputs
, 2023 Performing an additive decomposition of arbitrary functions of random elements is paramount for global sensitivity analysis and, therefore, the interpretation of black-box models. The well-known seminal work of Hoeffding characterized the summands in such a decomposition in the particular case of mutually independent inputs.
Idrissi, Marouane Il +4 more
openaire +2 more sources
Quantitative de Jong theorems in any dimension [PDF]
, 2016 We develop a new quantitative approach to a multidimensional version of the well-known {\it de Jong's central limit theorem} under optimal conditions, stating that a sequence of Hoeffding degenerate $U$-statistics whose fourth cumulants converge to zero ...
Döbler, Christian, Peccati, Giovanni
core +2 more sources
Inference for High-Dimensional Exchangeable Arrays [PDF]
Journal of the American Statistical Association, 2020 We consider inference for high-dimensional separately and jointly exchangeable arrays where the dimensions may be much larger than the sample sizes. For both exchangeable arrays, we first derive high-dimensional central limit theorems over the rectangles
Harold D. Chiang +2 more
semanticscholar +1 more source
Malliavin and dirichlet structures for independent random variables [PDF]
, 2018 On any denumerable product of probability spaces, we construct a Malliavin gradient and then a divergence and a number operator. This yields a Dirichlet structure which can be shown to approach the usual structures for Poisson and Brownian processes.
Decreusefond, Laurent +1 more
core +4 more sources
Orthogonal decomposition of finite population L-statistics
Lietuvos Matematikos Rinkinys, 2009 In this paper we study orthogonal decomposition of finite population L-statistics. We propose quite simple form of first two terms of such decomposition.
Andrius Čiginas
doaj +1 more source
Hoeffding decompositions and urn sequences
The Annals of Probability, 2008 Let \({\mathbf X}= X_1,X_2,\dots\) be an infinite exchangeable sequence of \(D\)- valued random variables, with \(D= \{d_1,\dots, d_m\}\). Let \(SU_0(X_1,\dots, X_n)= R\) and \(SU_k\), \(k= 1,\dots, n\), be the space of all random variables \[ F(X_1,\dots, X_n)= \sum\varphi(X_{j1},\dots, X_{jk})\tag{1} \] with sum over all \(1\leq j_1 1\) and \(k= 1 ...
El-Dakkak, Omar, Peccati, Giovanni
openaire +2 more sources