Fisher information, training and bias in Fourier regression models
Machine Learning: Science and Technology · 01.08.2026 · 7 (4) · 045048
DOI: 10.1088/2632-2153/ae8fb7 ↗Kurz gefasst
Fachartikel in der Zeitschrift Machine Learning: Science and Technology, online erschienen am 12.08.2026. Verfasst von Lorenzo Pastori und 2 weiteren Autor:innen. Die Arbeit nennt 89 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Federal Ministry for Economic Affairs and Climate Action, European Research Council, Gottfried Wilhelm Leibniz Prize.
Abstract (Originalsprache)
Motivated by the growing interest in quantum machine learning, in particular quantum neural networks (QNNs), we study how recently introduced evaluation metrics based on the Fisher information matrix (FIM) are effective for predicting their training and prediction performance. We exploit the equivalence between a broad class of QNNs and Fourier models, and study the interplay between the effective dimension (ED) and the bias of a model towards a given task, investigating how these affect the model’s training and performance. We show that for a model that is completely agnostic, or unbiased, towards the function to be learned, a higher ED likely results in a better trainability and performance. On the other hand, for models that are biased towards the function to be learned a lower ED is likely beneficial during training. To obtain these results, we derive an analytical expression of the FIM for Fourier models and identify the features controlling a model’s ED. This allows us to construct models with tunable ED and bias, and to compare their training. We furthermore introduce a tensor network representation of the considered Fourier models, which could be a tool of independent interest for the analysis of QNN models. Overall, these findings provide an explicit example of the interplay between geometrical properties, model-task alignment and training, which are relevant for the broader machine learning community.
Förderung
- Federal Ministry for Economic Affairs and Climate Action
- European Research Council
- Gottfried Wilhelm Leibniz Prize
Zitieren
APA
Pastori, L., Eyring, V., & Schwabe, M. (2026). Fisher information, training and bias in Fourier regression models. Machine Learning: Science and Technology, 7(4), 045048. https://doi.org/10.1088/2632-2153/ae8fb7
Vancouver
Pastori L, Eyring V, Schwabe M. Fisher information, training and bias in Fourier regression models. Machine Learning: Science and Technology. 2026;7(4):045048. doi:10.1088/2632-2153/ae8fb7
BibTeX
@article{Pastori2026,
author = {Pastori, Lorenzo and Eyring, Veronika and Schwabe, Mierk},
title = {Fisher information, training and bias in Fourier regression models},
journal = {Machine Learning: Science and Technology},
year = {2026},
volume = {7},
number = {4},
pages = {045048},
doi = {10.1088/2632-2153/ae8fb7}
}
EUVIMED