Curator's Take
AI Commentary
This article shows that the correlation fractal dimension D₂ can be used as a reliable “qubit budget” for angle‑encoded quantum kernels, preventing the notorious kernel collapse that plagues overly wide feature maps. By matching the number of encoded coordinates to D₂ rather than to conventional PCA thresholds, the authors keep the kernel geometrically expressive on both simulators and real IBM hardware, offering a practical guideline for designing compact yet powerful quantum machine‑learning pipelines. The result bridges recent insights into data‑dependent expressivity limits with concrete hardware‑aware recommendations, though it also highlights that the optimal budget varies with the chosen feature map and bandwidth settings.
— Mark Eatherly
Summary
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-angle and re-uploading encodings still live at the fractal q, but not when PCA-95% features are stacked onto those qubits. Shrinking the angle bandwidth moves the ZZ knee later; stretching it kills the kernel earlier. On IBM Quantum (ibm_fez, 256 shots, n=8) the one-layer ZZ kernel at the fractal width matches the exact kernel (MAE 0.021); past that width both hardware and simulator have collapsed. The ceiling is a property of the map-data pair at a stated bandwidth, not of the classical table alone.