Some properties of the normed alternating least squares (ALS) algorithm (Q3823780)
From MaRDI portal
!
This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use the normal view instead:
scientific article; zbMATH DE number 4098702
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | Some properties of the normed alternating least squares (ALS) algorithm |
scientific article; zbMATH DE number 4098702 |
Statements
Some properties of the normed alternating least squares (ALS) algorithm (English)
0 references
1988
0 references
normed alternating least squares algorithm
0 references
optimal scaling
0 references
linear
0 references
regression
0 references
constrained nonlinear optimization
0 references
projection methods
0 references
Convergence
0 references
polyhedral convex cone restrictions
0 references
implementation
0 references
algorithm
0 references
0 references
0 references
0 references
0 references
0.7590314745903015
0 references
0.759024441242218
0 references
0.7544116973876953
0 references
0.7450646758079529
0 references
0.7420894503593445
0 references
Convergence results are the main purpose of the paper. Remember that the ALS algorithm is designed to compute an optimal cardinal representation of qualitative data in the least squares sense. Especially the author proves that the global optimum can be found in the case of polyhedral convex cone restrictions using a finite set of different starting points. Also the practical implementation of the algorithm based on the author's theoretical result is pointed out.
0 references