Machine-learning optimized measurements of chaotic dynamical systems via the information bottleneck
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913272780816384 |
|---|---|
| author | Murphy, Kieran A. Bassett, Dani S. |
| author_facet | Murphy, Kieran A. Bassett, Dani S. |
| contents | Deterministic chaos permits a precise notion of a "perfect measurement" as one that, when obtained repeatedly, captures all of the information created by the system's evolution with minimal redundancy. Finding an optimal measurement is challenging, and has generally required intimate knowledge of the dynamics in the few cases where it has been done. We establish an equivalence between a perfect measurement and a variant of the information bottleneck. As a consequence, we can employ machine learning to optimize measurement processes that efficiently extract information from trajectory data. We obtain approximately optimal measurements for multiple chaotic maps and lay the necessary groundwork for efficient information extraction from general time series. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2311_04896 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Machine-learning optimized measurements of chaotic dynamical systems via the information bottleneck Murphy, Kieran A. Bassett, Dani S. Machine Learning Information Theory Chaotic Dynamics Deterministic chaos permits a precise notion of a "perfect measurement" as one that, when obtained repeatedly, captures all of the information created by the system's evolution with minimal redundancy. Finding an optimal measurement is challenging, and has generally required intimate knowledge of the dynamics in the few cases where it has been done. We establish an equivalence between a perfect measurement and a variant of the information bottleneck. As a consequence, we can employ machine learning to optimize measurement processes that efficiently extract information from trajectory data. We obtain approximately optimal measurements for multiple chaotic maps and lay the necessary groundwork for efficient information extraction from general time series. |
| title | Machine-learning optimized measurements of chaotic dynamical systems via the information bottleneck |
| topic | Machine Learning Information Theory Chaotic Dynamics |
| url | https://arxiv.org/abs/2311.04896 |