Explainable quantum regression algorithm with encoded data structure

Communications in Mathematical Physics · Springer Nature · 2026-11-10 · DOI: 10.1007/s42484-026-00453-x

Аннотация

Hybrid variational quantum algorithms are promising for solving practical problems in application areas, which include quantum machine learning, combinatorial optimization, and quantum chemistry simulation on noisy quantum computers. However, variational quantum algorithms (currently derived from randomized hardware-efficient ansätze or adaptive ansätze) become a black box, not trustworthy for model interpretation, and not to mention application deployment in informing critical decisions. In this paper, we construct the first interpretable quantum regression algorithm inherently, in which the quantum state exactly encodes the classical data table and the variational parameters correspond directly to the regression coefficients, which are real numbers by construction, providing a high degree of model interpretability and minimal cost to optimize due to the right expressiveness. We also exploit the encoded data structure to reduce the gate complexity of computing the regression map. To reduce circuit depth in nonlinear regression, our algorithm can be extended by directly constructing nonlinear features via classical preprocessing, such as independent encoded column vectors. By design, the model performance is determined by the cost function measurement results synchronous to the mean squared errors (MSE) for the regression models. We derive the read-out errors induced by one-hot encoding and compact encoding; the required physical qubit resources are exponentially compressed for the compact encoding to be favorable for noisy quantum devices. We also derive explicitly the data-aware sample complexity $$\varvec{\in } \varvec{\mathcal {O}}\left( \varvec{\sigma }^{\varvec{2}} \varvec{\ln } \varvec{(}\varvec{1}\varvec{/}\varvec{\alpha }\varvec{)}\varvec{/}\varvec{\epsilon }^{\varvec{2}}\right) $$ per classical optimization iteration under the error budget $$\varvec{\epsilon }$$ and confidence tolerance $$\varvec{\alpha }$$ for further empirical benchmarks.

Читать у издателя →

Похожие статьи