Exploration-Exploitation Tradeoff in Universal Lossy Compression
Fuente:
arXiv
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915358350245888 |
|---|---|
| author | Weinberger, Nir Zamir, Ram |
| author_facet | Weinberger, Nir Zamir, Ram |
| contents | Universal compression can learn the source and adapt to it either in a batch mode (forward adaptation), or in a sequential mode (backward adaptation). We recast the sequential mode as a multi-armed bandit problem, a fundamental model in reinforcement-learning, and study the trade-off between exploration and exploitation in the lossy compression case. We show that a previously proposed "natural type selection" scheme can be cast as a reconstruction-directed MAB algorithm, for sequential lossy compression, and explain its limitations in terms of robustness and short-block performance. We then derive and analyze robust cost-directed MAB algorithms, which work at any block length. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_20261 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Exploration-Exploitation Tradeoff in Universal Lossy Compression Weinberger, Nir Zamir, Ram Information Theory Machine Learning Universal compression can learn the source and adapt to it either in a batch mode (forward adaptation), or in a sequential mode (backward adaptation). We recast the sequential mode as a multi-armed bandit problem, a fundamental model in reinforcement-learning, and study the trade-off between exploration and exploitation in the lossy compression case. We show that a previously proposed "natural type selection" scheme can be cast as a reconstruction-directed MAB algorithm, for sequential lossy compression, and explain its limitations in terms of robustness and short-block performance. We then derive and analyze robust cost-directed MAB algorithms, which work at any block length. |
| title | Exploration-Exploitation Tradeoff in Universal Lossy Compression |
| topic | Information Theory Machine Learning |
| url | https://arxiv.org/abs/2506.20261 |