Metraipolis › archive › dc_dccbaf49eab2
FiGuRO: Intrinsic Dimension Estimation for Multi-Modal Data — arXiv:2608.10857
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.10857
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T06:19:28.145Z
- SHA-256 of the archived text
0450bff1494fd5a555113becdf2b0b5d3d213cb3983ee1cae3510ac641f28330- Stable URL of this page
https://metraipolis.com/documento/dc_dccbaf49eab2
How to cite
FiGuRO: Intrinsic Dimension Estimation for Multi-Modal Data — arXiv:2608.10857 — arXiv (en), https://arxiv.org/abs/2608.10857 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dccbaf49eab2 (Metraipolis archive dc_dccbaf49eab2, sha256 0450bff1494fd5a555113becdf2b0b5d3d213cb3983ee1cae3510ac641f28330)
BibTeX
@misc{dcdccbaf49eab2,
title = {FiGuRO: Intrinsic Dimension Estimation for Multi-Modal Data — arXiv:2608.10857},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.10857},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dccbaf49eab2; sha256 0450bff1494fd5a555113becdf2b0b5d3d213cb3983ee1cae3510ac641f28330},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.10857. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Determining the complexity, or Intrinsic Dimension (ID), of data is fundamental to efficient and interpretable representation learning. This is particularly challenging in multi-modal settings when trying to learn disentangled representations for shared and private information. Existing techniques leave a critical gap: they are often static, uni-modal, or in the case of contrastive methods, adapt only to the shared ID implicitly. We introduce Fidelity-Guided Rank Optimization (FiGuRO), a framework for approximating the ID of uni- and multi-modal data under constraints of model capacity and hyperparameters. FiGuRO learns the dimensions of low-rank projections using truncated singular value decomposition and an algorithm that determines when to reduce or increase dimension and in which latent space. Disentanglement of shared and private information arises as an emergent property of this optimization, eliminating the need for complex auxiliary loss functions. We demonstrate that FiGuRO outperforms existing ID estimation techniques and is more robust to hyperparameter changes. Across simulations and real-world data, FiGuRO captures distinct ID scales and varying subspace ratios, and decomposes shared and private information successfully. Furthermore, we show that FiGuRO can be applied to modern uni-modal pretrained models, enabling efficient, post-hoc disentanglement of multi-modal representations. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-12 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2608.10857 — 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 2026-10-19T06:11:45.096Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-12?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).