Embargament

Document embargat fins el 2027-08-06

Tipus de document

Article

Versió

Versió acceptada

Data de publicació

Tots els drets reservats

Si us plau utilitzeu sempre aquest identificador per citar o enllaçar aquest document: https://hdl.handle.net/2445/231220

Soft Quantum Kernels with Bias–Variance Optimization on Density Operator Manifolds

Títol de la revista

Director/Tutor

ISSN de la revista

Títol del volum

Resum

We introduce the Soft Quantum Kernel, a one-parameter family of positive-semidefinite kernels indexed by a softness parameter  and obtained by replacing the pure-state density operator of a standard quantum kernel with the output of a depolarizing channel. The construction traces a convex chord on the manifold of density operators between the pure-state kernel and the maximally mixed state, and admits a closed-form expression that separates an informative component, controlled by , from a uniform regularizing floor. The kernel is shown to satisfy the Mercer property, and an exact bias–variance decomposition of the associated kernel-ridge estimator is derived. The effective degrees of freedom depend continuously on , so that the joint minimization of the expected prediction error over  is a biconvex program admitting at least one interior stationary point under standard regularity, in which  acts as a spectral regularizer complementary to the Tikhonov penalty. The softness parameter thus admits a transparent statistical interpretation: it shrinks the kernel spectrum multiplicatively while adding a rank-one component, so that the Soft Quantum Kernel is best read as an interpretable spectral regularization scheme rather than as a new kernel class. A computationally free rule fixes  from the normalized Shannon entropy of an auxiliary uncertainty distribution and provides a principled entry point for cross-validated refinement. A multi-block extension is cast as a kernel-alignment problem over the unit simplex and admits a closed-form solution in the interior case. The framework is connected to Riemannian optimization on the cone of positive-definite matrices via the Bures–Wasserstein metric, linking the present results to geometric algorithms recently developed in this journal. Hardware validation on a superconducting quantum processor confirms that a Frobenius perturbation of the Gram matrix of order one fifth produces a downstream area-under-curve shift below one percent. We stress that the main experimental claim of the paper concerns the stability of the estimator under physical noise rather than its predictive accuracy; a Monte Carlo study on simulated data, including classical kernel and ensemble baselines, noise-injection experiments, and sensitivity analyses with respect to the initialization and the entropy binning, corroborates this claim in a controlled environment.

Citació

Citació

SÁEZ ORTUÑO, Laura, et al. Soft Quantum Kernels with Bias–Variance Optimization on Density Operator Manifolds. Journal of Optimization Theory and Applications. 2026. Vol. 210, num. 42. ISSN 0022-3239. [consulted: 10 of September of 2026]. Available at: https://hdl.handle.net/2445/231220

Exportar metadades

JSON - METS

Compartir registre