Activity Number:
|
669
- New Nonparametric Statistical Methods for High-Dimensional Data
|
Type:
|
Contributed
|
Date/Time:
|
Thursday, August 2, 2018 : 10:30 AM to 12:20 PM
|
Sponsor:
|
Section on Nonparametric Statistics
|
Abstract #329525
|
Presentation
|
Title:
|
Sequentially Weighted Nearest Neighbour Classifier
|
Author(s):
|
Mehdi Soleymani*
|
Companies:
|
The University of Auckland
|
Keywords:
|
Classification;
Nearest Neighbour;
Sequential bagging
|
Abstract:
|
We propose a sequential algorithm based on the sequential bagging algorithm for constructing a classifier. The new algorithm splits the learning set to two parts and uses the first part to replace the fixed class labels of the second part with a probability distribution. This modified portion of learning set will be used to predict new observations. We investigate the theoretical properties of the new algorithm. We further study the properties of the proposed method under stronger smoothness assumptions.
|
Authors who are presenting talks have a * after their name.