Abstract
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.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Mikulasch, F. A., & Zenke, F. (2026). Predictive Self-Supervised Learning Provably Identifies Stochastic Signals under Nuisance. https://omanscience.com/en/articles/predictive-self-supervised-learning-provably-identifies-stochastic-signals-under-nuisance
MLA 9
Mikulasch, Fabian A., and Friedemann Zenke. "Predictive Self-Supervised Learning Provably Identifies Stochastic Signals under Nuisance." https://omanscience.com/en/articles/predictive-self-supervised-learning-provably-identifies-stochastic-signals-under-nuisance.
Chicago (author–date)
Mikulasch, Fabian A., and Friedemann Zenke. 2026. "Predictive Self-Supervised Learning Provably Identifies Stochastic Signals under Nuisance." https://omanscience.com/en/articles/predictive-self-supervised-learning-provably-identifies-stochastic-signals-under-nuisance.
Harvard
Mikulasch, F. A. and Zenke, F. (2026) 'Predictive Self-Supervised Learning Provably Identifies Stochastic Signals under Nuisance', Available at: https://omanscience.com/en/articles/predictive-self-supervised-learning-provably-identifies-stochastic-signals-under-nuisance.
Vancouver
Mikulasch FA, Zenke F. Predictive Self-Supervised Learning Provably Identifies Stochastic Signals under Nuisance. https://omanscience.com/en/articles/predictive-self-supervised-learning-provably-identifies-stochastic-signals-under-nuisance
IEEE
F. A. Mikulasch, and F. Zenke, "Predictive Self-Supervised Learning Provably Identifies Stochastic Signals under Nuisance," https://omanscience.com/en/articles/predictive-self-supervised-learning-provably-identifies-stochastic-signals-under-nuisance.