搜索结果: 1-13 共查到“统计学其他学科 high-dimensional”相关记录13条 . 查询时间(0.09 秒)
Modelling interactions in high-dimensional data with Backtracking
Backtracking interactions Lasso parallel computing path algorithm.
2012/9/17
We study the problem of high-dimensional regression when there may be interacting vari-ables. We introduce a new idea called Backtracking, that can be incorporated into many existing high-dimensional ...
Changepoint detection for high-dimensional time series with missing data
Change point detection high-dimensional time series missing data
2012/9/17
This paper describes a novel approach to changepoint detection when the observed high-dimensional data may have missing elements. The performance of classical methods for changepoint detection typical...
Penalized estimation in high-dimensional hidden Markov models with state-specific graphical models
HMM Graphical Lasso Universal Regularization Model Selection MMDL Greedy Backwards Pruning Genome Biology Chromatin Modeling
2012/9/17
We consider penalized estimation in hidden Markov models (HMMs) with multi-variate Normal observations. In the moderate-to-large dimensional setting, estimation for HMMs remains challenging in practic...
Test for bandedness of high-dimensional covariance matrices and bandwidth estimation
Banded covariance matrix bandwidth estimation high data dimension largep, small n nonparametric.
2012/9/17
Motivated by the latest effort to employ banded matrices to esti-mate a high-dimensional covariance Σ, we propose a test for Σbeing banded with possible diverging bandwidth. The test is adaptive to th...
Parameter-Free High-Dimensional Screening Using Multiple Grouping of Variables
Parameter-Free High-Dimensional Screening Multiple Grouping Variables
2012/9/17
Screening is the problem of estimating a superset of the set of non-zero entries in an unknownp-dimensional vector β given nnoisy observations. In the high-dimensional regime, where p > n, screening a...
An Improved Data Assimilation Scheme for High Dimensional Nonlinear Systems
Bayesian Estimation Ensemble Data Assimilation Gaussian Sum Expansion Environmental Control
2012/9/17
Nonlinear/non-Gaussian ltering has broad applications in many areas of life sciences where either the dynamic is nonlinear and/or the probability density function of un-certain state is non-Gaussian....
Two-step estimation of high dimensional additive models
additive model group Lasso penalized least squares.
2012/9/19
This paper investigates the two-step estimation of a high dimensional additive regression model, in which the number of nonparametric additive components is potentially larger than the sample size but...
Finite sample posterior concentration in high-dimensional regression
asymptotics Bayesian compressible prior high-dimensional posterior contraction regression shrinkage prior.
2012/9/19
We study the behavior of the posterior distribution in ultra high-dimensional Bayesian Gaussian linear regression models havingp佲n,withpthe number of predictors and nthe sample size. In particular, ou...
Grouping Strategies and Thresholding for High Dimensional Linear Models
Structured sparsity Grouping, Learning Theory Non Linear Methods Block-thresholding coherence Wavelets
2012/9/19
The estimation problem in a high regression model with structured sparsity is investigated.An algorithm using a two steps block thresholding procedure called GR-LOL is provided.Convergence rates are p...
Resistant estimates for high dimensional and functional data based on random projections
Resistant estimates high dimensional functional data based
2011/7/5
In this paper we propose a new robust estimation method based on random projections which is adaptive, produces an automatic robust estimate, while being easy to compute for high or infinite dimension...
Group Lasso estimation of high-dimensional covariance matrices
Group Lasso ℓ 1 penalty high-dimensional covariance estimation basis expansion
2010/10/19
In this paper, we consider the Group Lasso estimator of the covariance matrix of a stochastic process corrupted by an additive noise. We propose to estimate the covariance matrix in a high-dimensiona...
Smoothing ℓ₁-penalized estimators for high-dimensional time-course data
Lasso Local least squares Multivariate regression Variable selection Weighted likelihood
2009/9/16
When a series of (related) linear models has to be estimated it is often appropriate to combine the different data-sets to construct more efficient estimators. We use ℓ₁-penalized estimato...
Selection of variables and dimension reduction in high-dimensional non-parametric regression
dimension reduction high dimension LASSO
2009/9/16
We consider a $l_1$-penalization procedure in the non-parametric Gaussian regression model. In many concrete examples, the dimension $d$ of the input variable $X$ is very large (sometimes depending on...