Accession Number:

ADA288294

Title:

Parallelizing Locally-Weighted Regression.

Descriptive Note:

Technical rept.,

Corporate Author:

GEORGE MASON UNIV FAIRFAX VA CENTER FOR COMPUTATIONAL STATISTICS

Personal Author(s):

• Fauntleroy, Julia C.
• Wegman, Edward J.

Report Date:

1994-10-01

Pagination or Media Count:

22.0

Abstract:

This paper focuses on a nonparametric regression technique known as locally-weighted regression or LOESS, LOESS is a computationally intensive technique which makes it naturally amenable to exploiting high performance computers. In this paper, we explore domain decomposition techniques for LOESS and study the performance of our algorithm on an Intel Paragon XPS A4 machine. We study both speedup and efficiency as a function of the number of nodes. Certain segments of the LOESS computation are shown to be fruitfully parallelized while others are essentially sequential and cannot be parallelized effectively.

Descriptors:

• *NONPARAMETRIC STATISTICS
• *REGRESSION ANALYSIS
• MATHEMATICAL MODELS
• ALGORITHMS
• COMPUTATIONS
• MULTIVARIATE ANALYSIS
• PARALLEL PROCESSING
• PROBLEM SOLVING
• SEQUENTIAL ANALYSIS
• MATHEMATICAL PROGRAMMING
• NODES
• WEIGHTING FUNCTIONS
• DEGREES OF FREEDOM

Subject Categories:

• Statistics and Probability
• Operations Research

Distribution Statement:

APPROVED FOR PUBLIC RELEASE