The high dimensionality of spectral data makes even tiny distributional differences from noise or artifacts perfectly separable by ML models, as explained by the Feldman-Hajek theorem and concentration of measure.
The Feldman-Hájek dichotomy for countable Gaussian mixtures and their asymptotic separability in high dimensions
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
The Infinite-Dimensional Nature of Spectroscopy and Why Models Succeed, Fail, and Mislead
The high dimensionality of spectral data makes even tiny distributional differences from noise or artifacts perfectly separable by ML models, as explained by the Feldman-Hajek theorem and concentration of measure.