Metraipolis › archive › dc_f4803c8ff16d

Predictive Self-Supervised Learning Provably Identifies Stochastic Signals under Nuisance — arXiv:2609.37789

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.37789
License (as archived)
CC0-1.0
Archived
2026-10-07T16:27:41.153Z
SHA-256 of the archived text
c74d096f0875e7200bb2fe5be90333a6c4bdba9f6139cc530076cff948d33995
Stable URL of this page
https://metraipolis.com/documento/dc_f4803c8ff16d

How to cite

Predictive Self-Supervised Learning Provably Identifies Stochastic Signals under Nuisance — arXiv:2609.37789 — arXiv (en), https://arxiv.org/abs/2609.37789 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f4803c8ff16d (Metraipolis archive dc_f4803c8ff16d, sha256 c74d096f0875e7200bb2fe5be90333a6c4bdba9f6139cc530076cff948d33995)
BibTeX
@misc{dcf4803c8ff16d,
  title = {Predictive Self-Supervised Learning Provably Identifies Stochastic Signals under Nuisance — arXiv:2609.37789},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.37789},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f4803c8ff16d; sha256 c74d096f0875e7200bb2fe5be90333a6c4bdba9f6139cc530076cff948d33995},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.37789. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Self-supervised learning (SSL) by predicting in latent space, without generating the input data itself, learns highly abstract, useful representations. Intuitively, this success is often attributed to its ability to discard nuisance information that is irrelevant to prediction. However, this poses a conundrum: both stochastic variation in a prediction-relevant latent signal and true nuisance make observations partly unpredictable; how could they be distinguished? Surprisingly, we prove that common SSL methods can achieve exactly this, by implicitly instantiating a latent-variable model with stochastic dynamics and observation-private nuisance. We trace their ability to recover the stochastic signal to two complementary principles: Predictive mutual information maximization ensures that representations retain the information needed for prediction, while latent distribution matching constrains how this information is encoded, thereby making the retained signal identifiable. We confirm this identifiability result in simulations for Gaussian predictors, which recover the true signal up to an affine transformation even in dynamic, nuisance-laden environments.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.AI).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.37789 — 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 2026-10-07T15:54:54.026Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).