Metraipolis › archive › dc_795cd1208937

Foundations of Independent Component Analysis — arXiv:2608.13229

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.13229
License (as archived)
CC0-1.0
Archived
2026-10-19T04:27:55.292Z
SHA-256 of the archived text
345ad19a131cf26bc1ec1ea4051bfafc622bd978e9d3899f74061d676b185028
Stable URL of this page
https://metraipolis.com/documento/dc_795cd1208937

How to cite

Foundations of Independent Component Analysis — arXiv:2608.13229 — arXiv (en), https://arxiv.org/abs/2608.13229 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_795cd1208937 (Metraipolis archive dc_795cd1208937, sha256 345ad19a131cf26bc1ec1ea4051bfafc622bd978e9d3899f74061d676b185028)
BibTeX
@misc{dc795cd1208937,
  title = {Foundations of Independent Component Analysis — arXiv:2608.13229},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.13229},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_795cd1208937; sha256 345ad19a131cf26bc1ec1ea4051bfafc622bd978e9d3899f74061d676b185028},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.13229. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We present the mathematical foundations of linear independent component analysis (ICA) models based on standard literature in a self-contained note. It is aimed at readers with a background in measure-theoretic probability theory. We first develop the theory of the characteristic functions of probability measures on $\mathbb{R}^d$, including their analyticity and the way in which they determine and characterise the distributions. We then focus on several identifiability results of ICA models with successively strengthened assumptions on the sources: from merely non-constant, to non-Gaussian, to Gaussian-free independent sources. Under the strictest assumptions, we show that the independent sources are identifiable up to translation, permutation, scales and signs, and this even in the presence of additive Gaussian noise. Furthermore, we present the online equivariant gradient descent ICA algorithm for recovering the independent sources from data, in the standard complete noiseless non-Gaussian ICA setting.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-14 in cs.LG).
Categorie arXiv: Statistics Theory (math.ST) ; Machine Learning (cs.LG); Probability (math.PR); Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2608.13229 — 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 2026-10-19T04:20:35.912Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).