Unifying Divergence Minimization and Statistical Inference via Convex Duality thumbnail
Pause
Mute
Subtitles
Playback speed
0.25
0.5
0.75
1
1.25
1.5
1.75
2
Full screen

Unifying Divergence Minimization and Statistical Inference via Convex Duality

Published on Feb 25, 20075484 Views

We unify divergence minimization and statistical inference by means of convex duality. In the process of doing so, we prove that the dual of approximate maximum entropy estimation is maximum a posteri

Chapter list

Kernel Methods - <br>Lecture 3: Inference and Convex Duality00:05
Course Overview00:30
Inverse Problems01:13
Example03:05
Maximum Entropy Principle04:33
Proof06:27
Proof (Part II)06:31
Approximate Moment Matching07:25
Previous Work09:36
Questions11:57
Fenchel Duality12:30
Key Theorem14:02
Application: Csiszar Divergence17:12
Application: KL-Divergence19:12
Application: Conditional Models20:18
Concentration of Empirical Means21:38
Risk Bounds23:08
Risk Bounds 0126:49
Optimization29:05
Shameless Plugs30:39