Informational Geometry
Add to your list(s)
Download to your calendar using vCal
If you have a question about this talk, please contact Rowan McAllister.
Abstract:
We will review the max-ent interpretation of exponential families, and it’s connection to information projections. After exploring some simple results about I-projections, Fisher information, and their relation to ideas in machine learning, we will explain how to geometrically interpret AdaBoost in this framework.
Optional Background:
Familiarity with Lagrange Multipliers/Lagrange duality will be helpful
This talk is part of the Machine Learning Reading Group @ CUED series.
This talk is included in these lists:
Note that ex-directory lists are not shown.
|