Metraipolis › archive › dc_e718ec570c06
Which Tasks Survive Self-Supervised Learning? — arXiv:2609.38393
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.38393
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T12:43:38.147Z
- SHA-256 of the archived text
502e88ca8dc6c4410e6de13fac2dceedff9a38001e45e7e60bd86ea659b682ca- Stable URL of this page
https://metraipolis.com/documento/dc_e718ec570c06
How to cite
Which Tasks Survive Self-Supervised Learning? — arXiv:2609.38393 — arXiv (en), https://arxiv.org/abs/2609.38393 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e718ec570c06 (Metraipolis archive dc_e718ec570c06, sha256 502e88ca8dc6c4410e6de13fac2dceedff9a38001e45e7e60bd86ea659b682ca)
BibTeX
@misc{dce718ec570c06,
title = {Which Tasks Survive Self-Supervised Learning? — arXiv:2609.38393},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.38393},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e718ec570c06; sha256 502e88ca8dc6c4410e6de13fac2dceedff9a38001e45e7e60bd86ea659b682ca},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.38393. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Same-instance self-supervised learning (SSL) learns representations by enforcing consistency across two views of the same underlying instance. This principle alone, however, does not determine which downstream tasks remain recoverable from the learned representation. We study this question through \emph{semantic recoverability}, defined as the amount of a task's posterior score captured by the represented function space. We show that, for centered and whitened representations, recoverability exactly determines directional class-distance-normalized variance (CDNV), controls few-shot nearest-centroid classification, and governs the strength of task-relevant semantic directions. The population linear probe and centroid axis coincide, and multiple well-recovered tasks approach a factorial centroid geometry. We then analyze a canonical two-view SSL objective and show that its population optimum spans the leading cross-view-stable modes of the associated two-view operator. This yields a closed-form spectral characterization of semantic recoverability: a downstream task is preserved to the extent that its posterior lies in the selected spectral subspace. We validate these predictions on synthetic and real datasets across several SSL methods, testing the predicted relationships among recoverability, directional geometry, spectral structure, and few-shot transfer. Together, these results give a task-level account of what information survives same-instance SSL and how the retained information appears in downstream geometry and transfer.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.AI).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.38393 — 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 2026-10-07T12:14:13.870Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).