Next: Search through Model-Space:
Up: Reconstructability Analysis (RA)
Previous: Join-procedure:
If
,
then f is called ``reconstructable'' from our model M. We can represent
the data without information loss by using model M and the assumptions made about
independencies seem to be correct.
A distribution f is regarded as ``approximately reconstructable'' from a model M if
the maximum entropy reconstruction
is sufficiently `close' to f
according to some distance-measure.
A well known class of distance-measures is the Minkowski-class of distances
(parameterized by
,
also known as L-norms:
which contain the Hamming-distance (L1), the Euclidean-distance (L2), and the
Max-distance ().
For measuring the accuracy of the model we are more interested in the information loss
of the maximum entropy reconstruction compared to the original distribution.
The following two non-symmetric measures are derived from information-theory:
Shannon's cross-entropy, also known as directed divergence
[28, pg. 279], [38, pg. 12]:
|
(21) |
and the relative information loss by normalizing Shannon's cross-entropy
over the possible information content (Hartley information)
[14, pg. 169],[26, pp. 228-229]:
|
(22) |
characterizes the percentage of information lost for fh
representing distribution f.
Next: Search through Model-Space:
Up: Reconstructability Analysis (RA)
Previous: Join-procedure:
Thomas Prang
1998-06-07