Singular leaning coefficients and efficiency in learning theory
Fuente:
arXiv
Salvato in:
| Autore principale: | |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917918408704000 |
|---|---|
| author | Aoyagi, Miki |
| author_facet | Aoyagi, Miki |
| contents | Singular learning models with non-positive Fisher information matrices include neural networks, reduced-rank regression, Boltzmann machines, normal mixture models, and others. These models have been widely used in the development of learning machines. However, theoretical analysis is still in its early stages. In this paper, we examine learning coefficients, which indicate the general learning efficiency of deep linear learning models and three-layer neural network models with ReLU units. Finally, we extend the results to include the case of the Softmax function. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_12747 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Singular leaning coefficients and efficiency in learning theory Aoyagi, Miki Machine Learning Algebraic Geometry Statistics Theory Singular learning models with non-positive Fisher information matrices include neural networks, reduced-rank regression, Boltzmann machines, normal mixture models, and others. These models have been widely used in the development of learning machines. However, theoretical analysis is still in its early stages. In this paper, we examine learning coefficients, which indicate the general learning efficiency of deep linear learning models and three-layer neural network models with ReLU units. Finally, we extend the results to include the case of the Softmax function. |
| title | Singular leaning coefficients and efficiency in learning theory |
| topic | Machine Learning Algebraic Geometry Statistics Theory |
| url | https://arxiv.org/abs/2501.12747 |