Target Factorization: Loss Geometry and Component Learning Dynamics
A class label can combine attributes, such as shape and color. We ask whether predicting these attributes separately makes each easier to learn. For cross-entropy, additive component scores remove an exact cross-component curvature term from the loss. This geometric separation does not guarantee faster learning. In a binary model, learned interactions slow additive-coordinate growth while accelerating predictive confidence: locally at unequal positive rates and at every confidence level above chance at unit rates. In a matched Boolean experiment with 12 initializations, a component reaches an accuracy threshold later when paired with an easier companion target. Allowing interactions reduces this delay from 24.00 to 14.58 updates (paired difference −9.42; exploratory 95% bootstrap interval [−14.33, −4.33]). Integrated prediction loss and error show the same direction without an accuracy threshold. Predictive dependence and backbone gradient alignment do not establish a causal explanation. A parity-target grid retains positive joint-versus-isolated training contrasts under exact output factorization, although its heads are not fully matched. Separating predictions therefore need not make their learning independent. Comparisons of output encodings should measure component-level predictions under explicit training controls.
Authors
- Yunguo Yu (ORCID: https://orcid.org/0009-0006-2003-3813)
Publication Details
- Journal
- Preprints.org
- Published
- 2026-11-16
- DOI
- https://doi.org/10.20944/preprints202611.1529.v1
- Primary Topic
- Neural Networks and Applications
- Type
- preprint