Alternate Learning and Compression Approaching R(D)
Information Theory
2024-11-06 v1 math.IT
Abstract
The inherent trade-off in on-line learning is between exploration and exploitation. A good balance between these two (conflicting) goals can achieve a better long-term performance. Can we define an optimal balance? We propose to study this question through a backward-adaptive lossy compression system, which exhibits a "natural" trade-off between exploration and exploitation.
Keywords
Cite
@article{arxiv.2411.03054,
title = {Alternate Learning and Compression Approaching R(D)},
author = {Ram Zamir and Kenneth Rose},
journal= {arXiv preprint arXiv:2411.03054},
year = {2024}
}
Comments
This paper was presented as a poster in the workshop `Learn 2 Compress', in ISIT 2024, Athens, Greece, July 2024. It was processed and reviewed in the Open Review system