稀疏编码自编码表达

From Ufldl

Jump to: navigation, search
(Sparse coding)
(Sparse coding[稀疏编码])
Line 96: Line 96:
Unfortunately, the objective function is non-convex, and hence impossible to optimize well using gradient-based methods. However, given <math>A</math>, the problem of finding <math>s</math> that minimizes <math>J(A, s)</math> is convex. Similarly, given <math>s</math>, the problem of finding <math>A</math> that minimizes <math>J(A, s)</math> is also convex. This suggests that we might try alternately optimizing for <math>A</math> for a fixed <math>s</math>, and then optimizing for <math>s</math> given a fixed <math>A</math>. It turns out that this works quite well in practice.
Unfortunately, the objective function is non-convex, and hence impossible to optimize well using gradient-based methods. However, given <math>A</math>, the problem of finding <math>s</math> that minimizes <math>J(A, s)</math> is convex. Similarly, given <math>s</math>, the problem of finding <math>A</math> that minimizes <math>J(A, s)</math> is also convex. This suggests that we might try alternately optimizing for <math>A</math> for a fixed <math>s</math>, and then optimizing for <math>s</math> given a fixed <math>A</math>. It turns out that this works quite well in practice.
-
 
[初译]
[初译]

Revision as of 08:13, 8 March 2013

Personal tools