|
Activity Number:
|
268
- A Unifying Theme for Interpretable Information Extraction from Data: The Stability Principle
|
|
Type:
|
Invited
|
|
Date/Time:
|
Tuesday, August 1, 2017 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
IMS
|
|
Abstract #322281
|
View Presentation
|
|
Title:
|
Stability, Uncertainty, and Bayesian Learning
|
|
Author(s):
|
Chris Holmes*
|
|
Companies:
|
University of Oxford
|
|
Keywords:
|
Bayesian nonparametrics ;
bootstrapping ;
stability ;
Bayesian bootstrap ;
ensemble learning ;
classification
|
|
Abstract:
|
We explore connections between model stability and Bayesian nonparametric learning in the absence of a known likelihood function. In the case of multiple competing models for the data we show how ensemble learning of models using principles of Bayesian nonparametric uncertainty and stability can enhance predictive performance and interpretation. Examples are given on a number of classification tasks.
|
Authors who are presenting talks have a * after their name.
Back to the full JSM 2017 program
|
