Explicit quantum surrogates for quantum kernel models

TL;DR

This paper introduces a hybrid quantum-classical method to create explicit quantum surrogates for implicit quantum kernel models, reducing prediction costs and addressing barren plateau challenges in quantum machine learning.

Contribution

It proposes a novel algorithm to construct explicit quantum surrogates from implicit models, combining their advantages and improving training and prediction efficiency.

Findings

EQS reduces prediction costs compared to implicit models.

The method mitigates barren plateau issues in quantum training.

Experimental results demonstrate improved model performance.

Abstract

Quantum machine learning (QML) leverages quantum states for data encoding, with key approaches being explicit models that use parameterized quantum circuits and implicit models that use quantum kernels. Implicit models often have lower training errors but face issues such as overfitting and high prediction costs, while explicit models can struggle with complex training and barren plateaus. We propose a quantum-classical hybrid algorithm to create an explicit quantum surrogate (EQS) for trained implicit models. This involves diagonalizing an observable from the implicit model and constructing a corresponding quantum circuit using an extended automatic quantum circuit encoding algorithm. The EQS framework reduces prediction costs, provides a powerful strategy to mitigate barren plateau issues, and combines the strengths of both QML approaches.