1mlpack_nmf(1) General Commands Manual mlpack_nmf(1)
2
3
4
6 mlpack_nmf - non-negative matrix factorization
7
9 mlpack_nmf [-h] [-v]
10
12 This program performs non-negative matrix factorization on the given
13 dataset, storing the resulting decomposed matrices in the specified
14 files. For an input dataset V, NMF decomposes V into two matrices W and
15 H such that
16
17 V = W * H
18
19 where all elements in W and H are non-negative. If V is of size (n x
20 m), then W will be of size (n x r) and H will be of size (r x m), where
21 r is the rank of the factorization (specified by --rank).
22
23 Optionally, the desired update rules for each NMF iteration can be cho‐
24 sen from the following list:
25
26 · multdist: multiplicative distance-based update rules (Lee and
27 Seung 1999)
28
29 · multdiv: multiplicative divergence-based update rules (Lee
30 and Seung 1999)
31
32 · als: alternating least squares update rules (Paatero and Tap‐
33 per 1994)
34
35 The maximum number of iterations is specified with --max_iterations,
36 and the minimum residue required for algorithm termination is specified
37 with --min_residue.
38
40 --input_file (-i) [string]
41 Input dataset to perform NMF on.
42
43 --rank (-r) [int]
44 Rank of the factorization.
45
47 --help (-h)
48 Default help info.
49
50 --info [string]
51 Get help on a specific module or option. Default value ''.
52
53 --max_iterations (-m) [int]
54 Number of iterations before NMF terminates (0 runs until conver‐
55 gence. Default value 10000.
56
57 --min_residue (-e) [double]
58 The minimum root mean square residue allowed for each iteration,
59 below which the program terminates. Default value 1e-05.
60
61 --seed (-s) [int]
62 Random seed. If 0, 'std::time(NULL)' is used. Default value 0.
63 --update_rules (-u) [string] Update rules for each iteration; (
64 multdist | multdiv | als ). Default value 'multdist'.
65
66 --verbose (-v)
67 Display informational messages and the full list of parameters
68 and timers at the end of execution.
69
70 --version (-V)
71 Display the version of mlpack.
72
74 --h_file (-H) [string]
75 File to save the calculated H matrix to. Default value ''.
76
77 --w_file (-W) [string]
78 File to save the calculated W matrix to. Default value ''.
79
82 For further information, including relevant papers, citations, and the‐
83 ory, For further information, including relevant papers, citations, and
84 theory, consult the documentation found at http://www.mlpack.org or
85 included with your consult the documentation found at
86 http://www.mlpack.org or included with your DISTRIBUTION OF MLPACK.
87 DISTRIBUTION OF MLPACK.
88
89
90
91 mlpack_nmf(1)