Data-driven neighborhood selection of a Gaussian field
نویسندگان
چکیده
منابع مشابه
Data-driven neighborhood selection of a Gaussian field
We study the non-parametric covariance estimation of a stationary Gaussian field X observed on a lattice. To tackle this issue, we have introduced a model selection procedure in a previous paper [Ver09]. This procedure amounts to selecting a neighborhood m̂ by a penalization method and estimating the covariance of X in the space of Gaussian Markov random fields (GMRFs) with neighborhood m̂. Such ...
متن کاملEfficient Neighborhood Selection for Gaussian Graphical Models
This paper addresses the problem of neighborhood selection for Gaussian graphical models. We present two heuristic algorithms: a forward-backward greedy algorithm for general Gaussian graphical models based on mutual information test, and a threshold-based algorithm for walk summable Gaussian graphical models. Both algorithms are shown to be structurally consistent, and efficient. Numerical res...
متن کاملData-Mining-Driven Neighborhood Search
Metaheuristic approaches based on neighborhood search escape local optimality by applying predefined rules and constraints, such as tabu restrictions (in tabu search), acceptance criteria (in simulated annealing), and shaking (in VNS). We propose a general approach that attempts to learn (offline) the guiding constraints that, when applied online, will result in effective escape directions from...
متن کاملIdentification of BKCa channel openers by molecular field alignment and patent data-driven analysis
In this work, we present the first comprehensive molecular field analysis of patent structures on how the chemical structure of drugs impacts the biological binding. This task was formulated as searching for drug structures to reveal shared effects of substitutions across a common scaffold and the chemical features that may be responsible. We used the SureChEMBL patent database, which prov...
متن کاملData-Driven Gaussian Component Selection for Fast GMM-Based Speaker Verification
In this paper, a fast likelihood calculation of Gaussian mixture model (GMM) is presented, by means of dividing the acoustic space into disjoint subsets and then assigning the most relevant Gaussians to each of them. The data-driven approach is explored to select Gaussian component which guarantees that the loss, brought by pre-discarding most useless Gaussians, can be easily controlled by a ma...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Computational Statistics & Data Analysis
سال: 2010
ISSN: 0167-9473
DOI: 10.1016/j.csda.2009.12.001