en-fr
en-de
en-sl
en
en-zh
en-es
0.25
0.5
0.75
1.25
1.5
1.75
2
Suboptimality of MDL and Bayes in Classification under Misspecification
Published on 2007-02-253217 Views
We show that forms of Bayesian and MDL learning that are often applied to classification problems can be *statistically inconsistent*. We present a large family of classifiers and a distribution such
Related categories
Presentation
Suboptimality of Bayes and MDL in Classification00:02
Our Result00:29
Why is this interesting?01:17
Menu02:39
Classification03:22
Classification Models04:26
Generalization Error05:05
Learning Algorithms06:02
Consistent Learning Algorithms06:38
Main Result08:09
Remainder of Talk13:07
Bayesian Learning of Classifiers13:40
classifiers probability distrs.14:53
Logistic transformation - intuition16:25
Definition of . 24:55
Issues/Remainder of Talk27:21
Scenario27:36
Scenario – II: Definition of true D29:35
Result: 31:16
Theorem 137:20
Theorem 1, extended 39:33
How ‘natural’ is scenario?42:46
Thm 2: full Bayes result is ‘tight’ 45:46
Theorem 247:38
Proof Sketch49:46
Wait a minute…55:35
Bayes predicts too well58:52
Bayesian Consistency Results01:00:11
Bayesian consistency under misspecification01:02:58
Conclusion01:05:21