The Thermodynamic Costs of Simple Linear Regression
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910234888372224 |
|---|---|
| author | D'Ambrosia, Samuel H. Daniels, Sultan M. DeWeese, Michael R. Sahai, Anant |
| author_facet | D'Ambrosia, Samuel H. Daniels, Sultan M. DeWeese, Michael R. Sahai, Anant |
| contents | The construction of models from data is a significant contributor to the energetic costs of computation. Because of this, understanding how foundational thermodynamic bounds apply to modeling algorithms will be increasingly important. Here, we study the thermodynamic costs of a basic and fundamental modeling algorithm: simple linear regression. Following Landauer, we approximate the thermodynamic lower bound on irreversibly performing both exact linear regression and linear regression via stochastic gradient descent as implemented on floating-point numbers. From this, we derive energycost aware scaling laws for the optimal dataset size for training a linear regression model given a generalization error dependent demand for inference. Additionally, we discuss a method to lower bound the entropy production from the mismatch cost for algorithms with continuous input variables. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_19195 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | The Thermodynamic Costs of Simple Linear Regression D'Ambrosia, Samuel H. Daniels, Sultan M. DeWeese, Michael R. Sahai, Anant Statistical Mechanics Information Theory Machine Learning The construction of models from data is a significant contributor to the energetic costs of computation. Because of this, understanding how foundational thermodynamic bounds apply to modeling algorithms will be increasingly important. Here, we study the thermodynamic costs of a basic and fundamental modeling algorithm: simple linear regression. Following Landauer, we approximate the thermodynamic lower bound on irreversibly performing both exact linear regression and linear regression via stochastic gradient descent as implemented on floating-point numbers. From this, we derive energycost aware scaling laws for the optimal dataset size for training a linear regression model given a generalization error dependent demand for inference. Additionally, we discuss a method to lower bound the entropy production from the mismatch cost for algorithms with continuous input variables. |
| title | The Thermodynamic Costs of Simple Linear Regression |
| topic | Statistical Mechanics Information Theory Machine Learning |
| url | https://arxiv.org/abs/2605.19195 |