Thouless-Anderson-Palmer Approach for Lossy Compression
Disordered Systems and Neural Networks
2009-11-10 v2
Abstract
We study an ill-posed linear inverse problem, where a binary sequence will be reproduced using a sparce matrix. According to the previous study, this model can theoretically provide an optimal compression scheme for an arbitrary distortion level, though the encoding procedure remains an NP-complete problem. In this paper, we focus on the consistency condition for a dynamics model of Markov-type to derive an iterative algorithm, following the steps of Thouless-Anderson-Palmer's. Numerical results show that the algorithm can empirically saturate the theoretical limit for the sparse construction of our codes, which also is very close to the rate-distortion function.
Cite
@article{arxiv.cond-mat/0310440,
title = {Thouless-Anderson-Palmer Approach for Lossy Compression},
author = {Tatsuto Murayama},
journal= {arXiv preprint arXiv:cond-mat/0310440},
year = {2009}
}
Comments
10 pages, 3 figures