Entropy, concentration, and learning: a statistical mechanics primer
Fuente:
arXiv
Guardado en:
| Autor principal: | |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913521071030272 |
|---|---|
| author | Balsubramani, Akshay |
| author_facet | Balsubramani, Akshay |
| contents | Artificial intelligence models trained through loss minimization have demonstrated significant success, grounded in principles from fields like information theory and statistical physics. This work explores these established connections through the lens of statistical mechanics, starting from first-principles sample concentration behaviors that underpin AI and machine learning. Our development of statistical mechanics for modeling highlights the key role of exponential families, and quantities of statistics, physics, and information theory. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_18630 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Entropy, concentration, and learning: a statistical mechanics primer Balsubramani, Akshay Machine Learning Statistical Mechanics Artificial Intelligence Information Theory Artificial intelligence models trained through loss minimization have demonstrated significant success, grounded in principles from fields like information theory and statistical physics. This work explores these established connections through the lens of statistical mechanics, starting from first-principles sample concentration behaviors that underpin AI and machine learning. Our development of statistical mechanics for modeling highlights the key role of exponential families, and quantities of statistics, physics, and information theory. |
| title | Entropy, concentration, and learning: a statistical mechanics primer |
| topic | Machine Learning Statistical Mechanics Artificial Intelligence Information Theory |
| url | https://arxiv.org/abs/2409.18630 |