Towards Weak Source Coding
Published in arXiv (Cornell University) • Sep 11, 2022
NobleIDNI8P18W35R46S55
Authors:
Aman Chawla
Abstract
In this paper, the authors provide a weak decoding version of the traditional source coding theorem of Claude Shannon. The central bound that is obtained is \[ χ>\log_ε(2^{-n(H(X)+ε)}) \] where \[ χ=\frac{\log(k)}{n(H(X)+ε)} \] and $k$ is the number of unsupervised learning classes formed out of the...
Finding related papers...
Discussions
(0)No comments yet
Be the first to share your thoughts!