Compressive Meta-Learning
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911106024341504 |
|---|---|
| author | Montserrat, Daniel Mas Bonet, David Perera, Maria Giró-i-Nieto, Xavier Ioannidis, Alexander G. |
| author_facet | Montserrat, Daniel Mas Bonet, David Perera, Maria Giró-i-Nieto, Xavier Ioannidis, Alexander G. |
| contents | The rapid expansion in the size of new datasets has created a need for fast and efficient parameter-learning techniques. Compressive learning is a framework that enables efficient processing by using random, non-linear features to project large-scale databases onto compact, information-preserving representations whose dimensionality is independent of the number of samples and can be easily stored, transferred, and processed. These database-level summaries are then used to decode parameters of interest from the underlying data distribution without requiring access to the original samples, offering an efficient and privacy-friendly learning framework. However, both the encoding and decoding techniques are typically randomized and data-independent, failing to exploit the underlying structure of the data. In this work, we propose a framework that meta-learns both the encoding and decoding stages of compressive learning methods by using neural networks that provide faster and more accurate systems than the current state-of-the-art approaches. To demonstrate the potential of the presented Compressive Meta-Learning framework, we explore multiple applications -- including neural network-based compressive PCA, compressive ridge regression, compressive k-means, and autoencoders. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_11090 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Compressive Meta-Learning Montserrat, Daniel Mas Bonet, David Perera, Maria Giró-i-Nieto, Xavier Ioannidis, Alexander G. Machine Learning Artificial Intelligence Computational Engineering, Finance, and Science Databases 68T07, 68T05, 68T09 I.2.6; I.5.1; G.3; H.2.8 The rapid expansion in the size of new datasets has created a need for fast and efficient parameter-learning techniques. Compressive learning is a framework that enables efficient processing by using random, non-linear features to project large-scale databases onto compact, information-preserving representations whose dimensionality is independent of the number of samples and can be easily stored, transferred, and processed. These database-level summaries are then used to decode parameters of interest from the underlying data distribution without requiring access to the original samples, offering an efficient and privacy-friendly learning framework. However, both the encoding and decoding techniques are typically randomized and data-independent, failing to exploit the underlying structure of the data. In this work, we propose a framework that meta-learns both the encoding and decoding stages of compressive learning methods by using neural networks that provide faster and more accurate systems than the current state-of-the-art approaches. To demonstrate the potential of the presented Compressive Meta-Learning framework, we explore multiple applications -- including neural network-based compressive PCA, compressive ridge regression, compressive k-means, and autoencoders. |
| title | Compressive Meta-Learning |
| topic | Machine Learning Artificial Intelligence Computational Engineering, Finance, and Science Databases 68T07, 68T05, 68T09 I.2.6; I.5.1; G.3; H.2.8 |
| url | https://arxiv.org/abs/2508.11090 |