en
0.25
0.5
0.75
1.25
1.5
1.75
2
The Sample Complexity of Dictionary Learning
Published on Aug 02, 20113714 Views
A large set of signals can sometimes be described sparsely using a dictionary, that is, every element can be represented as a linear combination of few elements from the dictionary. Algorithms for v
Related categories
Chapter list
The Sample Complexity of Dictionary Learning00:00
Common ground00:19
Applications01:09
Not just images01:32
Problem de nition - 102:12
Problem de nition - 202:37
Problem de nition - 303:30
Problem de nition - 404:40
Problem de nition - 504:49
Parameters in two problem domains - 104:57
Parameters in two problem domains - 205:04
Applications revisited05:34
Di culties - 106:05
Di culties - 206:34
Di culties - 306:47
Di culties - 407:05
State of optimization problem - 107:09
State of optimization problem - 207:20
State of optimization problem - 307:27
Generalization problem07:32
Compressability: A = Rλ - 108:13
Compressability: A = Rλ - 209:02
Compressability: A = Rλ - 309:17
Compressability: A = Rλ - 409:21
Compressability: A = Rλ - 509:23
Proof sketch for Rλ09:28
D → hHk ,D has singularities10:05
Stable dictionaries for Hk - 111:00
Stable dictionaries for Hk - 211:40
Stable dictionaries for Hk - 311:55
Sparsity: A = Hk12:16
Proof sketch for Hk: stability - 112:58
Proof sketch for Hk: stability - 213:24
Proof sketch for Hk: stability - 313:47
Proof sketch for Hk: connection - 114:07
Proof sketch for Hk: connection - 214:30
Proof sketch for Hk: connection - 314:32
Summary - 114:47
Summary - 214:57
Summary - 315:05
Open problems15:17