.\" Text automatically generated by txt2man
.TH mlpack_local_coordinate_coding 1 "11 January 2024" "mlpack-4.3.0" "User Commands"
.SH NAME
\fBmlpack_local_coordinate_coding \fP- local coordinate coding
.SH SYNOPSIS
.nf
.fam C
 \fBmlpack_local_coordinate_coding\fP [\fB-k\fP \fIint\fP] [\fB-i\fP \fIunknown\fP] [\fB-m\fP \fIunknown\fP] [\fB-l\fP \fIdouble\fP] [\fB-n\fP \fIint\fP] [\fB-N\fP \fIbool\fP] [\fB-s\fP \fIint\fP] [\fB-T\fP \fIunknown\fP] [\fB-o\fP \fIdouble\fP] [\fB-t\fP \fIunknown\fP] [\fB-V\fP \fIbool\fP] [\fB-c\fP \fIunknown\fP] [\fB-d\fP \fIunknown\fP] [\fB-M\fP \fIunknown\fP] [\fB-h\fP \fB-v\fP] 
.fam T
.fi
.fam T
.fi
.SH DESCRIPTION


An implementation of Local Coordinate Coding (LCC), which codes data that
approximately lives on a manifold using a variation of l1-norm regularized
sparse coding. Given a dense data matrix X with n points and d dimensions,
LCC seeks to find a dense dictionary matrix D with k atoms in d dimensions,
and a coding matrix Z with n points in k dimensions. Because of the
regularization method used, the atoms in D should lie close to the manifold on
which the data points lie.
.PP
The original data matrix X can then be reconstructed as D * Z. Therefore,
this program finds a representation of each point in X as a sparse linear
combination of atoms in the dictionary D.
.PP
The coding is found with an algorithm which alternates between a dictionary
step, which updates the dictionary D, and a coding step, which updates the
coding matrix Z.
.PP
To run this program, the input matrix X must be specified (with \fB-i\fP), along
with the number of atoms in the dictionary (\fB-k\fP). An initial dictionary may
also be specified with the '\fB--initial_dictionary_file\fP (\fB-i\fP)' parameter. The
l1-norm regularization parameter is specified with the '\fB--lambda\fP (\fB-l\fP)'
parameter.
.PP
For example, to run LCC on the dataset 'data.csv' using 200 atoms and an
l1-regularization parameter of 0.1, saving the dictionary '\fB--dictionary_file\fP
(\fB-d\fP)' and the codes into '\fB--codes_file\fP (\fB-c\fP)', use
.PP
$ \fBmlpack_local_coordinate_coding\fP \fB--training_file\fP data.csv \fB--atoms\fP 200 \fB--lambda\fP
0.1 \fB--dictionary_file\fP dict.csv \fB--codes_file\fP codes.csv
.PP
The maximum number of iterations may be specified with the '\fB--max_iterations\fP
(\fB-n\fP)' parameter. Optionally, the input data matrix X can be normalized before
coding with the '\fB--normalize\fP (\fB-N\fP)' parameter.
.PP
An LCC model may be saved using the '\fB--output_model_file\fP (\fB-M\fP)' output
parameter. Then, to encode new points from the dataset 'points.csv' with the
previously saved model 'lcc_model.bin', saving the new codes to
\(cqnew_codes.csv', the following command can be used:
.PP
$ \fBmlpack_local_coordinate_coding\fP \fB--input_model_file\fP lcc_model.bin \fB--test_file\fP
points.csv \fB--codes_file\fP new_codes.csv
.RE
.PP

.SH OPTIONAL INPUT OPTIONS 

.TP
.B
\fB--atoms\fP (\fB-k\fP) [\fIint\fP]
Number of atoms in the dictionary. Default value 0. 
.TP
.B
\fB--help\fP (\fB-h\fP) [\fIbool\fP]
Default help info. 
.TP
.B
\fB--info\fP [string]
Print help on a specific option. Default value ''. 
.TP
.B
\fB--initial_dictionary_file\fP (\fB-i\fP) [\fIunknown\fP]
Optional initial dictionary. 
.TP
.B
\fB--input_model_file\fP (\fB-m\fP) [\fIunknown\fP]
Input LCC model. 
.TP
.B
\fB--lambda\fP (\fB-l\fP) [\fIdouble\fP]
Weighted l1-norm regularization parameter.  Default value 0. 
.TP
.B
\fB--max_iterations\fP (\fB-n\fP) [\fIint\fP]
Maximum number of iterations for LCC (0 indicates no limit). Default value 0. 
.TP
.B
\fB--normalize\fP (\fB-N\fP) [\fIbool\fP]
If set, the input data matrix will be normalized before coding. 
.TP
.B
\fB--seed\fP (\fB-s\fP) [\fIint\fP]
Random seed. If 0, 'std::time(NULL)' is used.  Default value 0. 
.TP
.B
\fB--test_file\fP (\fB-T\fP) [\fIunknown\fP]
Test points to encode. 
.TP
.B
\fB--tolerance\fP (\fB-o\fP) [\fIdouble\fP]
Tolerance for objective function. Default value 0.01. 
.TP
.B
\fB--training_file\fP (\fB-t\fP) [\fIunknown\fP]
Matrix of training data (X). 
.TP
.B
\fB--verbose\fP (\fB-v\fP) [\fIbool\fP]
Display informational messages and the full list of parameters and timers at the end of execution. 
.TP
.B
\fB--version\fP (\fB-V\fP) [\fIbool\fP]
Display the version of mlpack.  
.SH OPTIONAL OUTPUT OPTIONS 

.TP
.B
\fB--codes_file\fP (\fB-c\fP) [\fIunknown\fP]
Output codes matrix. 
.TP
.B
\fB--dictionary_file\fP (\fB-d\fP) [\fIunknown\fP]
Output dictionary matrix. 
.TP
.B
\fB--output_model_file\fP (\fB-M\fP) [\fIunknown\fP]
Output for trained LCC model.
.SH ADDITIONAL INFORMATION

For further information, including relevant papers, citations, and theory,
consult the documentation found at http://www.mlpack.org or included with your
distribution of mlpack.