Universal Feature Selection with Noisy Observations and Weak Symmetry Conditions
Abstract
This paper relaxes the restrictive symmetry conditions adopted in [4], [5] and extends their universal feature selection framework to accommodate noisy observations as well as attribute structures that may exhibit directional preferences. We introduce the notion of weak spherical symmetry, quantified by second-moment distances, which allows controlled deviations from rotational invariance. Under this relaxed condition, we develop a universal feature selection framework based on the singular value decomposition of the canonical dependence matrix computed from noisy data. Our main result shows that the selected features achieve asymptotically optimal error exponents up to a residual term that depends on the symmetry deviation δ and the noise levels η1, η2. When δ, η1, η2 are relatively small, our result recovers that of [5], thereby demonstrating that exact spherical symmetry is unnecessary. Overall, our findings highlight the robustness of the selection framework against second-moment deviations and observation noise, thereby broadening its applicability across diverse inference tasks and providing a theoretically grounded tool for universal feature selection in practical scenarios.
Related
- Universal Distributed Feature Extraction Complementary to Side Information via H-Score
- Linear-Time Multivariate Unsupervised Feature Selection Using Nyström-Based Entropy Approximation
- Learning from pandemics: Feature selection and clustering for robust digital disease nowcasting
- Symmetry-Aware Feature Learning: A Polynomial Separation for Multi-Index Models
- Variable Selection for Feature-Based Newsvendor
BibTeX
@misc{tang2026universal,
title = {{Universal Feature Selection with Noisy Observations and Weak Symmetry Conditions}},
author = {Dier Tang and Guangyue Han},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2605.09396},
eprint = {2605.09396},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2605.09396},
}
RIS
TY - UNPB
TI - Universal Feature Selection with Noisy Observations and Weak Symmetry Conditions
AU - Dier Tang
AU - Guangyue Han
PY - 2026
DA - 2026/09/15
PB - arXiv
DO - 10.48550/arxiv.2605.09396
UR - https://arxiv.org/abs/2605.09396
AB - This paper relaxes the restrictive symmetry conditions adopted in [4], [5] and extends their universal feature selection framework to accommodate noisy observations as well as attribute structures that may exhibit directional preferences. We introduce the notion of weak spherical symmetry, quantified by second-moment distances, which allows controlled deviations from rotational invariance. Under this relaxed condition, we develop a universal feature selection framework based on the singular value decomposition of the canonical dependence matrix computed from noisy data. Our main result shows that the selected features achieve asymptotically optimal error exponents up to a residual term that depends on the symmetry deviation δ and the noise levels η_1, η_2. When δ, η_1, η_2 are relatively small, our result recovers that of [5], thereby demonstrating that exact spherical symmetry is unnecessary. Overall, our findings highlight the robustness of the selection framework against second-moment deviations and observation noise, thereby broadening its applicability across diverse inference tasks and providing a theoretically grounded tool for universal feature selection in practical scenarios.
ER -