Exponential Bounds of Mean Error for the Nearest Neighbor Estimates of Regression Functions.
Abstract
This paper establishes an expontential bound of the mean deviation between m sub n (x) and m (x) given the training sample z subn = (x sub 1), ...,X sub n, under the conditions as weak as possible. This is a substantial improvement on Beck's results.
Document Details
- Document Type
- Technical Report
- Publication Date
- Nov 01, 1985
- Accession Number
- ADA166156
Entities
People
- L. C. Zhao
Organizations
- University of Pittsburgh