Information Scrambling in Quantum Neural Networks

by   Huitao Shen, et al.

Quantum neural networks are one of the promising applications for near-term noisy intermediate-scale quantum computers. A quantum neural network distills the information from the input wavefunction into the output qubits. In this Letter, we show that this process can also be viewed from the opposite direction: the quantum information in the output qubits is scrambled into the input. This observation motivates us to use the tripartite information, a quantity recently developed to characterize information scrambling, to diagnose the training dynamics of quantum neural networks. We empirically find strong correlation between the dynamical behavior of the tripartite information and the loss function in the training process, from which we identify that the training process has two stages for randomly initialized networks. In the early stage, the network performance improves rapidly and the tripartite information increases linearly with a universal slope, meaning that the neural network becomes less scrambled than the random unitary. In the latter stage, the network performance improves slowly while the tripartite information decreases. We present evidences that the network constructs local correlations in the early stage and learns large-scale structures in the latter stage. We believe this two-stage training dynamics is universal and is applicable to a wide range of problems. Our work builds bridges between two research subjects of quantum neural networks and information scrambling, which opens up a new perspective to understand quantum neural networks.


page 1

page 2

page 3

page 4


Scalable Quantum Convolutional Neural Networks

With the beginning of the noisy intermediate-scale quantum (NISQ) era, q...

Quantum Neural Machine Learning - Backpropagation and Dynamics

The current work addresses quantum machine learning in the context of Qu...

Multi-stage Neural Networks: Function Approximator of Machine Precision

Deep learning techniques are increasingly applied to scientific problems...

Training Neural Networks with Universal Adiabatic Quantum Computing

The training of neural networks (NNs) is a computationally intensive tas...

Analyzing Convergence in Quantum Neural Networks: Deviations from Neural Tangent Kernels

A quantum neural network (QNN) is a parameterized mapping efficiently im...

RoQNN: Noise-Aware Training for Robust Quantum Neural Networks

Quantum Neural Network (QNN) is a promising application towards quantum ...

Another Look at Quantum Neural Computing

The term quantum neural computing indicates a unity in the functioning o...

Please sign up or login with your details

Forgot password? Click here to reset