Metraipolis › archive › dc_c853af4b414f
Universal Sample-Based Embeddings of Higher-Order Objects — arXiv:2610.19899
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.19899
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T14:18:46.222Z
- SHA-256 of the archived text
0bcdfb6efe23c617477e0eff0413d52566d64eb117cb7cde79ab9e4f1dd22415- Stable URL of this page
https://metraipolis.com/documento/dc_c853af4b414f
How to cite
Universal Sample-Based Embeddings of Higher-Order Objects — arXiv:2610.19899 — arXiv (en), https://arxiv.org/abs/2610.19899 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c853af4b414f (Metraipolis archive dc_c853af4b414f, sha256 0bcdfb6efe23c617477e0eff0413d52566d64eb117cb7cde79ab9e4f1dd22415)
BibTeX
@misc{dcc853af4b414f,
title = {Universal Sample-Based Embeddings of Higher-Order Objects — arXiv:2610.19899},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.19899},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c853af4b414f; sha256 0bcdfb6efe23c617477e0eff0413d52566d64eb117cb7cde79ab9e4f1dd22415},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.19899. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Neural networks operate naturally on finite-dimensional vectors, yet many problems require reasoning about higher-order objects such as distributions, functions, and graphs. Such objects capture relationships within a ground set and rarely admit an explicit compact representation. Moreover, we typically want a compact representation not of a single higher-order object but of an entire family of such objects, including members unseen during training. While a few approaches exist for particular object types, none is designed to work across object types. We propose a unified framework that represents any higher-order object as a fixed-size embedding vector learned over a family of such objects. An encoder maps an object, seen only through a finite set of samples, to an embedding, and a domain-specific decoder supplies the training signal by modeling the object conditioned on that embedding. Since the encoder works only from samples, one architecture serves different object types. Because the decoder is a model already suited to single instances of the object type, the framework inherits that model's native operations and inductive biases. We instantiate the framework on distributions, functions, and graphs. In each case we show that a single trained model represents an entire family and generalizes to members unseen during training. Furthermore, we demonstrate the downstream utility of these embeddings: interpolating distributions in embedding space, solving differential equations in embedding space, and predicting unseen edges from a graph's embedding. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.19899 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-15T13:53:35.669Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).