Representation Learning via Quantum Neural Tangent Kernels

Abstract

Variational quantum circuits are used in quantum machine learning and variational quantum simulation tasks. Designing good variational circuits or predicting how well they perform for given learning or optimization tasks is still unclear. Here we discuss these problems, analyzing variational quantum circuits using the theory of neural tangent kernels. We define quantum neural tangent kernels, and derive dynamical equations for their associated loss function in optimization and learning tasks. We analytically solve the dynamics in the frozen limit, or lazy training regime, where variational angles change slowly and a linear perturbation is good enough. We extend the analysis to a dynamical setting, including quadratic corrections in the variational angles. We then consider hybrid quantum-classical architecture and define a large-width limit for hybrid kernels, showing that a hybrid quantum-classical neural network can be approximately Gaussian. The results presented here show limits for which analytical understandings of the training dynamics for variational quantum circuits, used for quantum machine learning and optimization problems, are possible. These analytical results are supported by numerical simulations of quantum machine learning experiments.

Efficient Quantum Feature Extraction for CNN-based Learning

“…Besides, it is noted that quantum neural tangent kernel (QNTK) theory [51][52][53] is developed recently, which can be applied to QNNs.…”

Surviving The Barren Plateau in Variational Quantum Circuits with Bayesian Learning Initialization

“…In the second, fast, part we use the best parameter set from the slow part to initialize a local optimizer. This is now highly likely to reach the global optimum, since we start in the correct region and there is no longer a barren plateau [49].…”

Provable Advantage in Quantum Phase Learning via Quantum Kernel Alphatron

“…Tremendous classical kernel methods [45,46] have been proposed to learn the non-linear functions or decision boundaries. With the rapid development of quantum computers, there is a growing interest in exploring whether the quantum kernel method can surpass the classical kernel [35,36,39,[47][48][49][50][51][52][53][54][55][56][57][58][59][60][61]. Here we leverage the quantum kernel as our kernel function, which is defined as…”