They are designed to exploit low effective dimensions and include sparse grid methods as special case.
These include sparse sampling designs, leveraging of physiological data to quantify anticipated changes in PK, conducting the trial in silico before its execution in vivo, and the overall evaluation of potential study designs for their likelihood of quantifying the (changes in) PK parameters of interest.
These notably include sparse coding methods and deep neural networks.
These techniques include sparse representation, real time re-sampling, and the wavelet applications.
These algorithms include sparse Bayes [9], Bayesian compressive sensing (BCS) [10] and the fast Bayesian matching pursuit (FBMP) [11].
Parametric approaches include sparse representations using overcomplete dictionaries [12 14, 25 28], extraction of features from the time-frequency distributions such as the energy in different frequency bands, computation of higher order joint moments [29, 30], and entropy [31].
To support interpretation of PCs in terms of a priori variable groups, rather than just individual variables, sparse PCA methods have recently been extended to include structured sparse penalties [ 23, 24], such as the group lasso [ 25].
This method uses a Bayesian approach to include both sparse and smooth "optimized priors" on the STRFs.
(1) Gaussian graphical model: From the methodological point of view, it is desired to include the sparse Gaussian graphical model (GGM) approach for estimating the gene network under the multivariate normal assumption from a microarray data set.
Bayesian methods present an alternative way to deal with datasets including sparse data, and Bayesian analyses are now easily implemented using appropriate software.
