Bounds between contraction coefficients
In this paper, we delineate how the contraction coefficient of the strong data processing inequality for KL divergence can be used to learn likelihood models. We then present an alternative formulation that forces the input KL divergence to vanish, and achieves a contraction coefficient equivalent t...
Main Authors: | Makur, Anuran, Zheng, Lizhong |
---|---|
Other Authors: | Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science |
Format: | Article |
Language: | en_US |
Published: |
Institute of Electrical and Electronics Engineers (IEEE)
2017
|
Online Access: | http://hdl.handle.net/1721.1/112984 https://orcid.org/0000-0002-2978-8116 https://orcid.org/0000-0002-6108-0222 |
Similar Items
-
Information contraction and decomposition
by: Makur, Anuran.
Published: (2019) -
Polynomial Singular Value Decompositions of a Family of Source-Channel Models
by: Makur, Anuran, et al.
Published: (2021) -
Probabilistic Clustering using Maximal Matrix Norm Couplings
by: Qiu, David, et al.
Published: (2021) -
A study of local approximations in information theory
by: Makur, Anuran
Published: (2015) -
An efficient algorithm for information decomposition and extraction
by: Makur, Anuran, et al.
Published: (2018)