0.25
0.5
0.75
1.25
1.5
1.75
2
Feature Selection via Detecting Ineffective Features
Published on Aug 26, 20133756 Views
Consider the regression problem with a response variable Y and with a feature vector X. For the regression function m(x) = E{Y | X = x}, we introduce a new and simple estimator of the minimum mean s
Related categories
Chapter list
Feature Selection via Detecting Ineffective Features00:00
Outline - 100:16
Outline - 200:51
Problem description00:54
Application & methods - 101:32
Application & methods - 201:37
Application & methods - 301:44
Application & methods (cont’d)02:03
Some asymptotic theory for LASSO - 102:53
Some asymptotic theory for LASSO - 203:31
Some asymptotic theory for LASSO - 303:58
Some asymptotic theory for LASSO - 405:12
Parameter selection for variable selection - 105:20
Parameter selection for variable selection - 206:03
Parameter selection for variable selection - 306:18
Summary LASSO: Pros vs. Cons - 108:06
Summary LASSO: Pros vs. Cons - 208:36
Outline - 308:55
Theoretical aspects - 109:11
Theoretical aspects - 209:54
Theoretical aspects (cont’d) - 110:40
Theoretical aspects (cont’d) - 211:07
Detection of inefficient features - 113:17
Detection of inefficient features - 214:31
Detection of inefficient features - 314:35
Detection of inefficient features - 414:41
Detection of inefficient features (cont’d) - 115:43
Detection of inefficient features (cont’d) - 215:51
Detection of inefficient features (cont’d) - 316:07
Detection of inefficient features (cont’d) - 416:44
Issue with the test statistic - 116:44
Issue with the test statistic - 217:07
Issue with the test statistic - 317:14
Issue with the test statistic - 417:39
Issue with the test statistic - 518:10
Modification of test statistic18:13
Limit distribution of the test statistic - 118:57
Limit distribution of the test statistic - 219:06
Limit distribution of the test statistic - 320:04
Limit distribution of the test statistic - 421:40
Limit distribution of the test statistic - 521:47
Limit distribution of the test statistic (cont’d) - 121:50
Empirical verification of the theorem - 123:06
Limit distribution of the test statistic (cont’d) - 224:03
Empirical verification of the theorem - 224:16
Outline - 424:39
Toy example - 124:42
Toy example - 225:14
Bosting housing data - 126:14
Bosting housing data - 226:35
Boston housing data (cont’d) - 126:41
Boston housing data (cont’d) - 229:14
Boston housing data (cont’d) - 329:18
Outline - 529:20
Conclusion - 129:20
Conclusion - 229:36
Untitled29:53