Physics of Learning: A Lagrangian perspective to different learning paradigms
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912604781281280 |
|---|---|
| author | Guo, Siyuan Schölkopf, Bernhard |
| author_facet | Guo, Siyuan Schölkopf, Bernhard |
| contents | We study the problem of building an efficient learning system. Efficient learning processes information in the least time, i.e., building a system that reaches a desired error threshold with the least number of observations. Building upon least action principles from physics, we derive classic learning algorithms, Bellman's optimality equation in reinforcement learning, and the Adam optimizer in generative models from first principles, i.e., the Learning $\textit{Lagrangian}$. We postulate that learning searches for stationary paths in the Lagrangian, and learning algorithms are derivable by seeking the stationary trajectories. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_21049 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Physics of Learning: A Lagrangian perspective to different learning paradigms Guo, Siyuan Schölkopf, Bernhard Machine Learning Neural and Evolutionary Computing We study the problem of building an efficient learning system. Efficient learning processes information in the least time, i.e., building a system that reaches a desired error threshold with the least number of observations. Building upon least action principles from physics, we derive classic learning algorithms, Bellman's optimality equation in reinforcement learning, and the Adam optimizer in generative models from first principles, i.e., the Learning $\textit{Lagrangian}$. We postulate that learning searches for stationary paths in the Lagrangian, and learning algorithms are derivable by seeking the stationary trajectories. |
| title | Physics of Learning: A Lagrangian perspective to different learning paradigms |
| topic | Machine Learning Neural and Evolutionary Computing |
| url | https://arxiv.org/abs/2509.21049 |