SparseMap |
- LLR embedding is still impractical
|
- For large databases,
, are very large
|
- Dimensionality of embedded space is large
|
- For large sized
, time to determine the corresponding dimension by computing is large
|
- SparseMap proposes two practical heuristics
|
- Compute
by considering some (and not all) ![](images/img737.png)
|
|
- This is a way to avoid computing all
distances
|
|
is an upper bound of ![](images/img735.png)
|
- Reduce dimensionality by retaining some (and not all)
![](images/image008.gif)
|
|
- Greedy resampling: Delete
's that contributes largest to stress
|
|
- Sample only some object pairs when computing stress
|
|