SOURCE-LINKED INTELLIGENCE

Fractal dimension predicts quantum kernel collapse in angle-encoded data

arXiv · AI, language, vision and robotics · article · Aug 31, 2026 · UTC

Angle-encoded quantum kernels on tabular data collapse when the feature map is wider than the intrinsic dimension of the data. We propose the correlation fractal dimension D2 as an a priori qubit budget: encode D2 coordinates chosen by FD-ASE instead of the PCA-95% width or all E attributes. On nine data sets and a statevector simulator (n= 32), a one-layer ZZ fidelity kernel at q=D2 stays geometrically alive while the same kernel at the PCA-95% width has already collapsed. The budget is map-dependent: product-state and IQP maps overshoot it; a second ZZ layer undershoots it. Packed dense-angl

Read original source ↗ Open in workspace

recordType

paper

region

Global