Convergence of Smoothed Empirical Measures with Applications to Entropy Estimation
© 1963-2012 IEEE. This paper studies convergence of empirical measures smoothed by a Gaussian kernel. Specifically, consider approximating P* Nσ, for Nσ ≜ N (0,σ 2 I d), by hat P n∗ Nσ under different statistical distances, where hat P n is the empirical measure. We examine the convergence in terms...
Main Authors: | , , , |
---|---|
Other Authors: | |
Format: | Article |
Language: | English |
Published: |
Institute of Electrical and Electronics Engineers (IEEE)
2021
|
Online Access: | https://hdl.handle.net/1721.1/135991 |