Type: | Package |
Title: | Robust Kernel Unsupervised Methods |
Version: | 0.1.1.1 |
Author: | Md Ashad Alam |
Maintainer: | Md Ashad Alam <malam@tulane.edu> |
Description: | Robust kernel center matrix, robust kernel cross-covariance operator for kernel unsupervised methods, kernel canonical correlation analysis, influence function of identifying significant outliers or atypical objects from multimodal datasets. Alam, M. A, Fukumizu, K., Wang Y.-P. (2018) <doi:10.1016/j.neucom.2018.04.008>. Alam, M. A, Calhoun, C. D., Wang Y.-P. (2018) <doi:10.1016/j.csda.2018.03.013>. |
License: | GPL-3 |
Encoding: | UTF-8 |
Imports: | stats, graphics |
NeedsCompilation: | no |
Packaged: | 2022-06-22 04:48:39 UTC; hornik |
Repository: | CRAN |
Date/Publication: | 2022-06-22 04:50:17 UTC |
Kernel Matrix Using Guasian Kernel
Description
Many radial basis function kernels, such as the Gaussian kernel, map X into a infinte dimensional space. While the Gaussian kernel has a free parameter (bandwidth), it still follows a number of theoretical properties such as boundedness, consistence, universality, robustness etc. It is the most applicable kernel of the positive definite kernel based methods.
Usage
gkm(X)
Arguments
X |
a data matrix. |
Details
Many radial basis function kernels, such as the Gaussian kernel, map input sapce into a infinite dimensional space. The Gaussian kernel has a a number of theoretical properties such as boundedness, consistence, universality and robustness, etc.
Value
K |
a Gram/ kernel matrix |
Author(s)
Md Ashad Alam <malam@tulane.edu>
References
Md. Ashad Alam, Hui-Yi Lin, HOng-Wen Deng, Vince Calhour Yu-Ping Wang (2018), A kernel machine method for detecting higher order interactions in multimodal datasets: Application to schizophrenia, Journal of Neuroscience Methods, Vol. 309, 161-174.
Md Ashad Alam, Kenji Fukumizu and Yu-Ping Wang (2018), Influence Function and Robust Variant of Kernel Canonical Correlation Analysis, Neurocomputing, Vol. 304 (2018) 12-29.
M. Romanazzi (1992), Influence in canonical correlation analysis, Psychometrika vol 57(2) (1992) 237-259.
Examples
##Dummy data:
X<-matrix(rnorm(1000),100)
gkm(X)
A helper function
Description
#An matrices dicomposition function
Usage
gm3edc(Amat, Bmat, Cmat)
Arguments
Amat |
a square matrix |
Bmat |
a square matrix |
Cmat |
a square matrix |
Author(s)
Md Ashad Alam <malam@tulane.edu>
A helper function
Description
#An matrices dicomposition function
Usage
gmedc(A, B = diag(nrow(A)))
Arguments
A |
a square matrix |
B |
a diagonal matrix |
Author(s)
Md Ashad Alam <malam@tulane.edu>
A helper function
Description
###An function to adjust
Usage
gmi(X, tol = sqrt(.Machine$double.eps))
Arguments
X |
a square matrix |
tol |
a real value |
Author(s)
Md Ashad Alam <malam@tulane.edu>
Hampel's psi function
Description
##The ratio of the first derivative of the Hampel loss fuction to the argument. Tuning constants are fixed in different quintiles.
Usage
hadr(u)
Arguments
u |
vector values |
Value
a real value
Author(s)
Md Ashad Alam <malam@tulane.edu>
References
Md Ashad Alam, Kenji Fukumizu and Yu-Ping Wang (2018), Influence Function and Robust Variant of Kernel Canonical Correlation Analysis, Neurocomputing, Vol. 304 (2018) 12-29.
M. Romanazzi (1992), Influence in canonical correlation analysis, Psychometrika vol 57(2) (1992) 237-259.
See Also
A Hampel loss function
Description
#Tuning constants of the Hampel loss fuction are fixed in different quintiles of the arguments.
Usage
halfun(u)
Arguments
u |
vector of values. |
Value
comp1 |
a real number |
Author(s)
Md Ashad Alam <malam@tulane.edu>
References
Md Ashad Alam, Kenji Fukumizu and Yu-Ping Wang (2018), Influence Function and Robust Variant of Kernel Canonical Correlation Analysis, Neurocomputing, Vol. 304 (2018) 12-29.
M. Romanazzi (1992), Influence in canonical correlation analysis, Psychometrika vol 57(2) (1992) 237-259.
See Also
See Also as hulfun
, hadr
, hudr
Objective function
Description
Objective function of Hampel's loss fucntion
Usage
halofun(x)
Arguments
x |
vector values |
Value
a real value
Author(s)
Md Ashad Alam <malam@tulane.edu>
References
Md Ashad Alam, Kenji Fukumizu and Yu-Ping Wang (2018), Influence Function and Robust Variant of Kernel Canonical Correlation Analysis, Neurocomputing, Vol. 304 (2018) 12-29.
M. Romanazzi (1992), Influence in canonical correlation analysis, Psychometrika vol 57(2) (1992) 237-259.
See Also
See also as hulofun
Huber's psi function
Description
The ratio of the first derivative of the Huber loss fuction to the argument. Tuning constants is fixed as a meadian vlue.
Usage
hudr(x)
Arguments
x |
vector values |
Value
y |
a real value |
Author(s)
Md Ashad Alam <malam@tulane.edu>
References
Md Ashad Alam, Kenji Fukumizu and Yu-Ping Wang (2018), Influence Function and Robust Variant of Kernel Canonical Correlation Analysis, Neurocomputing, Vol. 304 (2018) 12-29.
M. Romanazzi (1992), Influence in canonical correlation analysis, Psychometrika vol 57(2) (1992) 237-259.
See Also
See also as hadr
A Huber loss function
Description
Tuning constants of the Huber loss fuction are fixed in different quintiles of the arguments.
Usage
hulfun(x)
Arguments
x |
a vector values |
Details
Tuning constants of the Huber fuction is fixed as a median.
Value
a real number
Author(s)
Md Ashad Alam <malam@tulane.edu>
References
Md Ashad Alam, Kenji Fukumizu and Yu-Ping Wang (2018), Influence Function and Robust Variant of Kernel Canonical Correlation Analysis, Neurocomputing, Vol. 304 (2018) 12-29.
M. Romanazzi (1992), Influence in canonical correlation analysis, Psychometrika vol 57(2) (1992) 237-259.
See Also
See also as halfun
Objective function
Description
Objective function of Huber's loss fucntion
Usage
hulofun(x)
Arguments
x |
vector values |
Value
a real value
Author(s)
Md Ashad Alam <malam@tulane.edu>
References
Md Ashad Alam, Kenji Fukumizu and Yu-Ping Wang (2018), Influence Function and Robust Variant of Kernel Canonical Correlation Analysis, Neurocomputing, Vol. 304 (2018) 12-29.
M. Romanazzi (1992), Influence in canonical correlation analysis, Psychometrika vol 57(2) (1992) 237-259.
See Also
See Also as halofun
, ~~~
Kernel Matrix Using Identity-by-state Kernel
Description
For GWASs, a kernel captures the pairwise similarity across a number of SNPs in each gene. Kernel projects the genotype data from original high dimensional space to a feature space. One of the more popular kernels used for genomics similarity is the identity-by-state (IBS) kernel (non- parametric function of the genotypes)
Usage
ibskm(Z)
Arguments
Z |
a data matrix |
Details
For genome-wide association study, a kernel captures the pairwise similarity across a number of SNPs in each gene. Kernel projects the genotype data from original high dimensional space to a feature space. One popular kernel used for genomics similarity is the identity-by-state (IBS) kernel, The IBS kernel does not need any assumption on the type of genetic interactions.
Value
K |
a Gram/ kernel matrix |
Author(s)
Md Ashad Alam <malam@tulane.edu>
References
Md. Ashad Alam, Hui-Yi Lin, HOng-Wen Deng, Vince Calhour Yu-Ping Wang (2018), A kernel machine method for detecting higher order interactions in multimodal datasets: Application to schizophrenia, Journal of Neuroscience Methods, Vol. 309, 161-174.
Md Ashad Alam, Kenji Fukumizu and Yu-Ping Wang (2018), Influence Function and Robust Variant of Kernel Canonical Correlation Analysis, Neurocomputing, Vol. 304 (2018) 12-29.
M. Romanazzi (1992), Influence in canonical correlation analysis, Psychometrika vol 57(2) (1992) 237-259.
See Also
Examples
##Dummy data:
X <- matrix(rnorm(200),50)
ibskm(X)
Influence Funciton of Canonical Correlation Analysis
Description
##To define the robustness in statistics, different approaches have been pro- posed, for example, the minimax approach, the sensitivity curve, the influence function (IF) and the finite sample breakdown point. Due to its simplic- ity, the IF is the most useful approach in statistical machine learning
Usage
ifcca(X, Y, gamma = 1e-05, ncomps = 2, jth = 1)
Arguments
X |
a data matrix index by row |
Y |
a data matrix index by row |
gamma |
the hyper-parameters |
ncomps |
the number of canonical vectors |
jth |
the influence function of the jth canonical vector |
Value
iflccor |
Influence value of the data by linear canonical correalation |
Author(s)
Md Ashad Alam <malam@tulane.edu>
References
Md Ashad Alam, Kenji Fukumizu and Yu-Ping Wang (2018), Influence Function and Robust Variant of Kernel Canonical Correlation Analysis, Neurocomputing, Vol. 304 (2018) 12-29.
M. Romanazzi (1992), Influence in canonical correlation analysis, Psychometrika vol 57(2) (1992) 237-259.
See Also
Examples
##Dummy data:
X <- matrix(rnorm(500),100); Y <- matrix(rnorm(500),100)
ifcca(X,Y, 1e-05, 2, 2)
Influence Function of Multiple Kernel Canonical Analysis
Description
## To define the robustness in statistics, different approaches have been pro- posed, for example, the minimax approach, the sensitivity curve, the influence function (IF) and the finite sample breakdown point. Due to its simplic- ity, the IF is the most useful approach in statistical machine learning.
Usage
ifmkcca(xx, yy, zz, kernel = "rbfdot", gamma = 1e-05, ncomps = 1, jth=1)
Arguments
xx |
a data matrix index by row |
yy |
a data matrix index by row |
zz |
a data matrix index by row |
kernel |
a positive definite kernel |
ncomps |
the number of canonical vectors |
gamma |
the hyper-parameters. |
jth |
the influence function of the jth canonical vector |
Value
iflccor |
Influence value of the data by multiple kernel canonical correalation |
Author(s)
Md Ashad Alam <malam@tulane.edu>
References
Md Ashad Alam, Kenji Fukumizu and Yu-Ping Wang (2018), Influence Function and Robust Variant of Kernel Canonical Correlation Analysis, Neurocomputing, Vol. 304 (2018) 12-29.
M. Romanazzi (1992), Influence in canonical correlation analysis, Psychometrika vol 57(2) (1992) 237-259.
See Also
See also as ifcca
Examples
##Dummy data:
X <- matrix(rnorm(500),100); Y <- matrix(rnorm(500),100); Z <- matrix(rnorm(500),100)
ifmkcca(X,Y, Z, "rbfdot", 1e-05, 2, 1)
Influence Function of Robust Kernel Canonical Analysis
Description
##To define the robustness in statistics, different approaches have been pro- posed, for example, the minimax approach, the sensitivity curve, the influence function (IF) and the finite sample breakdown point. Due to its simplic- ity, the IF is the most useful approach in statistical machine learning.
Usage
ifrkcca(X, Y, lossfu = "Huber", kernel = "rbfdot", gamma = 0.00001, ncomps = 10, jth = 1)
Arguments
X |
a data matrix index by row |
Y |
a data matrix index by row |
lossfu |
a loss function: square, Hampel's or Huber's loss |
kernel |
a positive definite kernel |
gamma |
the hyper-parameters |
ncomps |
the number of canonical vectors |
jth |
the influence function of the jth canonical vector |
Value
ifrkcor |
Influence value of the data by robust kernel canonical correalation |
ifrkxcv |
Influence value of cnonical vector of X dataset |
ifrkycv |
Influence value of cnonical vector of Y dataset |
Author(s)
Md Ashad Alam <malam@tulane.edu>
References
Md Ashad Alam, Kenji Fukumizu and Yu-Ping Wang (2018), Influence Function and Robust Variant of Kernel Canonical Correlation Analysis, Neurocomputing, Vol. 304 (2018) 12-29.
M. Romanazzi (1992), Influence in canonical correlation analysis, Psychometrika vol 57(2) (1992) 237-259.
See Also
Examples
##Dummy data:
X <- matrix(rnorm(500),100); Y <- matrix(rnorm(500),100)
ifrkcca(X,Y, lossfu = "Huber", kernel = "rbfdot", gamma = 0.00001, ncomps = 10, jth = 2)
A helper function
Description
#A function ..............
Usage
lcv(X, Y, res)
Arguments
X |
a matrix |
Y |
a matrix |
res |
a real value |
Author(s)
Md Ashad Alam <malam@tulane.edu>
Kernel Matrix Using Linear Kernel
Description
The linear kernel is used by the underlying Euclidean space to define the similarity measure. Whenever the dimensionality is high, it may allow for more complexity in the function class than what we could measure and assess otherwise
Usage
lkm(X)
Arguments
X |
a data matrix |
Details
The linear kernel is used by the underlying Euclidean space to define the similarity measure. Whenever the dimensionality of the data is high, it may allow for more complexity in the function class than what we could measure and assess otherwise.
Value
K |
a kernel matrix. |
Author(s)
Md Ashad Alam <malam@tulane.edu>
References
Md. Ashad Alam, Hui-Yi Lin, HOng-Wen Deng, Vince Calhour Yu-Ping Wang (2018), A kernel machine method for detecting higher order interactions in multimodal datasets: Application to schizophrenia, Journal of Neuroscience Methods, Vol. 309, 161-174.
Md Ashad Alam, Kenji Fukumizu and Yu-Ping Wang (2018), Influence Function and Robust Variant of Kernel Canonical Correlation Analysis, Neurocomputing, Vol. 304 (2018) 12-29.
Md Ashad Alam, Vince D. Calhoun and Yu-Ping Wang (2018), Identifying outliers using multiple kernel canonical correlation analysis with application to imaging genetics, Computational Statistics and Data Analysis, Vol. 125, 70- 85
See Also
Examples
##Dummy data:
X <- matrix(rnorm(500),100)
lkm(X)
Bandwidth of the Gaussian kernel
Description
A median of the pairwise distance of the data
Usage
mdbw(X)
Arguments
X |
a data matrix |
Details
While the Gaussian kernel has a free parameter (bandwidth), it still follows a number of theoretical properties such as boundedness, consistenc, universality, robustness, etc. It is the most applicable one. In a Gaussian RBF kernel, we need to select an appropriate a bandwidth. It is well known that the parameter has a strong influence on the result of kernel methods. For the Gaussian kernel, we can use the median of the pairwise distance as a bandwidth.
Value
s |
a median of the pairwise distance of the X dataset |
Author(s)
Md Ashad Alam <malam@tulane.edu>
References
Md. Ashad Alam, Hui-Yi Lin, HOng-Wen Deng, Vince Calhour Yu-Ping Wang (2018), A kernel machine method for detecting higher order interactions in multimodal datasets: Application to schizophrenia, Journal of Neuroscience Methods, Vol. 309, 161-174.
Md. Ashad Alam, Kenji Fukumizu and Yu-Ping Wang (2018), Influence Function and Robust Variant of Kernel Canonical Correlation Analysis, Neurocomputing, Vol. 304 (2018) 12-29.
Md. Ashad Alam and Kenji Fukumizu (2015), Higher-order regularized kernel canonical correlation analysis, International Journal of Pattern Recognition and Artificial Intelligence, Vol. 29(4) 1551005.
Arthu Gretton, Kenji. Fukumizu, C. H. Teo, L. Song, B. Scholkopf and A. Smola (2008), A Kernel statistical test of independence, in Advances in Neural Information Processing Systems, Vol. 20 585–592.
See Also
Examples
##Dummy data:
X <- matrix(rnorm(1000),100)
mdbw(X)
A helper function
Description
# A function
Usage
medc(A, fn = sqrt)
Arguments
A |
a matrix |
fn |
a funciton |
Author(s)
Md Ashad Alam <malam@tulane.edu>
A helper function
Description
## A function
Usage
mvnod(n = 1, mu, Sigma, tol = 1e-06, empirical = FALSE, EISPACK = FALSE)
Arguments
n |
an integer number |
mu |
a real value |
Sigma |
a real value |
tol |
a curection factor |
empirical |
a logical value |
EISPACK |
a logical value. TRUE for a complex values. |
Author(s)
Md Ashad Alam <malam@tulane.edu>
A helper function
Description
A function
Usage
ranuf(p)
Arguments
p |
a real value |
Author(s)
Md Ashad Alam <malam@tulane.edu>
Robust kernel canonical correlation analysis
Description
#A robust correlation
Usage
rkcca(X, Y, lossfu = "Huber", kernel = "rbfdot", gamma = 1e-05, ncomps = 10)
Arguments
X |
a data matrix index by row |
Y |
a data matrix index by row |
lossfu |
a loss function: square, Hampel's or Huber's loss |
kernel |
a positive definite kernel |
gamma |
the hyper-parameters |
ncomps |
the number of canonical vectors |
Value
An S3 object containing the following slots:
rkcor |
Robsut kernel canonical correlation |
rxcoef |
Robsut kernel canonical coficient of X dataset |
rycoef |
Robsut kernel canonical coficient of Y dataset |
rxcv |
Robsut kernel canonical vector of X dataset |
rycv |
Robsut kernel canonical vector of Y dataset |
Author(s)
Md Ashad Alam <malam@tulane.edu>
References
Md Ashad Alam, Kenji Fukumizu and Yu-Ping Wang (2018), Influence Function and Robust Variant of Kernel Canonical Correlation Analysis, Neurocomputing, Vol. 304 (2018) 12-29.
M. Romanazzi (1992), Influence in canonical correlation analysis, Psychometrika vol 57(2) (1992) 237-259.
See Also
See also as ifcca
, rkcca
, ifrkcca
Examples
##Dummy data:
X <- matrix(rnorm(1000),100); Y <- matrix(rnorm(1000),100)
rkcca(X,Y, "Huber", "rbfdot", 1e-05, 10)
Robust kernel cross-covariance opetator
Description
# A function
Usage
rkcco(X, Y, lossfu = "Huber", kernel = "rbfdot", gamma = 1e-05)
Arguments
X |
a data matrix index by row |
Y |
a data matrix index by row |
lossfu |
a loss function: square, Hampel's or Huber's loss |
kernel |
a positive definite kernel |
gamma |
the hyper-parameters |
Value
rkcmx |
Robust kernel center matrix of X dataset |
rkcmy |
Robust kernel center matrix of Y dataset |
rkcmx |
Robust kernel covariacne operator of X dataset |
rkcmy |
Robust kernel covariacne operator of Y dataset |
rkcmx |
Robust kernel cross-covariacne operator of X and Y datasets |
Author(s)
Md Ashad Alam <malam@tulane.edu>
References
Md Ashad Alam, Kenji Fukumizu and Yu-Ping Wang (2018), Influence Function and Robust Variant of Kernel Canonical Correlation Analysis, Neurocomputing, Vol. 304 (2018) 12-29.
M. Romanazzi (1992), Influence in canonical correlation analysis, Psychometrika vol 57(2) (1992) 237-259.
See Also
See also as rkcca
snpfmridata
, ifrkcca
Examples
##Dummy data:
X <- matrix(rnorm(2000),200); Y <- matrix(rnorm(2000),200)
rkcco(X,Y, "Huber","rbfdot", 1e-05)
Robsut Kernel Center Matrix
Description
# A functioin
Usage
rkcm(X, lossfu = "Huber", kernel = "rbfdot")
Arguments
X |
a data matrix index by row |
lossfu |
a loss function: square, Hampel's or Huber's loss |
kernel |
a positive definite kernel |
Value
rkcm |
a square robust kernel center matrix |
Author(s)
Md Ashad Alam <malam@tulane.edu>
References
Md Ashad Alam, Kenji Fukumizu and Yu-Ping Wang (2018), Influence Function and Robust Variant of Kernel Canonical Correlation Analysis, Neurocomputing, Vol. 304 (2018) 12-29.
Md Ashad Alam, Vince D. Calhoun and Yu-Ping Wang (2018), Identifying outliers using multiple kernel canonical correlation analysis with application to imaging genetics, Computational Statistics and Data Analysis, Vol. 125, 70- 85
See Also
See also as ifcca
, rkcca
, ifrkcca
Examples
##Dummy data:
X <- matrix(rnorm(2000),200); Y <- matrix(rnorm(2000),200)
rkcm(X, "Huber","rbfdot")
A helper fuction
Description
#A function to calcualte generalized logit function.
Usage
rlogit(x)
Arguments
x |
a real value to be tranformed |
Author(s)
Md Ashad Alam <malam@tulane.edu>
An example of imaging genetics data to calcualte influential observations from two view data
Description
#A function
Usage
snpfmridata(n = 300, gamma=0.00001, ncomps = 2, jth = 1)
Arguments
n |
the sample size |
gamma |
the hyper-parameters |
ncomps |
the number of canonical vectors |
jth |
the influence function of the jth canonical vector |
Value
IFCCAID |
Influence value of canonical correlation analysis for the ideal data |
IFCCACD |
Influence value of canonical correlation analysis for the contaminated data |
IFKCCAID |
Influence value of kernel canonical correlation analysis for the ideal data |
IFKCCACD |
Influence value of kernel canonical correlation analysis for the contaminated data |
IFHACCAID |
Influence value of robsut (Hampel's loss) canonical correlation analysis for the ideal data |
IFHACCACD |
Influence value of robsut (Hampel's loss) canonical correlation analysis for the contaminated data |
IFHUCCAID |
Influence value of robsut (Huber's loss) canonical correlation analysis for the ideal data |
IFHUCCACD |
Influence value of robsut (Huber's loss) canonical correlation analysis for the contaminated data |
Author(s)
Md Ashad Alam <malam@tulane.edu>
References
Md Ashad Alam, Kenji Fukumizu and Yu-Ping Wang (2018), Influence Function and Robust Variant of Kernel Canonical Correlation Analysis, Neurocomputing, Vol. 304 (2018) 12-29.
Md Ashad Alam, Vince D. Calhoun and Yu-Ping Wang (2018), Identifying outliers using multiple kernel canonical correlation analysis with application to imaging genetics, Computational Statistics and Data Analysis, Vol. 125, 70- 85
See Also
See also as rkcca
, ifrkcca
, snpfmrimth3D
Examples
##Dummy data:
n<-100
snpfmridata(n, 0.00001, 10, jth = 1)
An example of imaging genetics and epi-genetics data to calcualte influential observations from three view data
Description
#A function
Usage
snpfmrimth3D(n = 500, gamma = 1e-05, ncomps = 1, jth=1)
Arguments
n |
the sample size |
gamma |
the hyper-parameters |
ncomps |
the number of canonical vectors |
jth |
the influence function of the jth canonical vector |
Value
IFim |
Influence value of multiple kernel canonical correlation analysis for the ideal data |
IFcm |
Influence value of multiple kernel canonical correlation analysis for the contaminated data |
Author(s)
Md Ashad Alam <malam@tulane.edu>
References
Md Ashad Alam, Kenji Fukumizu and Yu-Ping Wang (2018), Influence Function and Robust Variant of Kernel Canonical Correlation Analysis, Neurocomputing, Vol. 304 (2018) 12-29.
Md Ashad Alam, Vince D. Calhoun and Yu-Ping Wang (2018), Identifying outliers using multiple kernel canonical correlation analysis with application to imaging genetics, Computational Statistics and Data Analysis, Vol. 125, 70- 85
See Also
See also as rkcca
, snpfmridata
, ifrkcca
Examples
##Dummy data:
n<-100
snpfmrimth3D(n, 0.00001, 10, 1)
A helper function
Description
### A function to a measure of a system's real point computing power
Usage
udtd(x)
Arguments
x |
a real value |
Author(s)
Md Ashad Alam <malam@tulane.edu>