
This paper explores the connection between backward-adaptive lossy compression and online learning, specifically focusing on the Natural Type Selection (NTS) algorithm and its ability to approach the rate-distortion bound by balancing exploration and exploitation.


coremsg

alternate-learning-and-compression-approaching-the-rate-distortion-bound


Alternate Learning and Compression Approaching the Rate-Distortion Bound


title_rewrite


This paper presents a unified framework for distributed source coding, multiple description coding, and source coding with side information at decoders, characterizing their multi-letter rate-distortion regions for general correlated sources using constrained-random number generators.


distributed-source-coding-multiple-description-coding-and-source-coding-with-side-information-at-decoders-using-constrained-random-number-generators-a-unified-approach-to-characterizing-multi-letter-rate-distortion-regions-for-general-correlated-sources


Distributed Source Coding, Multiple Description Coding, and Source Coding with Side Information at Decoders Using Constrained-Random Number Generators: A Unified Approach to Characterizing Multi-letter Rate-Distortion Regions for General Correlated Sources
