Symmetry-guided gradient descent for quantum neural networks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bian, Kaiming, Zhang, Shitao, Meng, Fei, Zhang, Wen, Dahlsten, Oscar
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910564410720256
author Bian, Kaiming
Zhang, Shitao
Meng, Fei
Zhang, Wen
Dahlsten, Oscar
author_facet Bian, Kaiming
Zhang, Shitao
Meng, Fei
Zhang, Wen
Dahlsten, Oscar
contents Many supervised learning tasks have intrinsic symmetries, such as translational and rotational symmetry in image classifications. These symmetries can be exploited to enhance performance. We formulate the symmetry constraints into a concise mathematical form. We design two ways to adopt the constraints into the cost function, thereby shaping the cost landscape in favour of parameter choices which respect the given symmetry. Unlike methods that alter the neural network circuit ansatz to impose symmetry, our method only changes the classical post-processing of gradient descent, which is simpler to implement. We call the method symmetry-guided gradient descent (SGGD). We illustrate SGGD in entanglement classification of Werner states and in a binary classification task in a 2-D feature space. In both cases, the results show that SGGD can accelerate the training, improve the generalization ability, and remove vanishing gradients, especially when the training data is biased.
format Preprint
id arxiv_https___arxiv_org_abs_2404_06108
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Symmetry-guided gradient descent for quantum neural networks
Bian, Kaiming
Zhang, Shitao
Meng, Fei
Zhang, Wen
Dahlsten, Oscar
Quantum Physics
Many supervised learning tasks have intrinsic symmetries, such as translational and rotational symmetry in image classifications. These symmetries can be exploited to enhance performance. We formulate the symmetry constraints into a concise mathematical form. We design two ways to adopt the constraints into the cost function, thereby shaping the cost landscape in favour of parameter choices which respect the given symmetry. Unlike methods that alter the neural network circuit ansatz to impose symmetry, our method only changes the classical post-processing of gradient descent, which is simpler to implement. We call the method symmetry-guided gradient descent (SGGD). We illustrate SGGD in entanglement classification of Werner states and in a binary classification task in a 2-D feature space. In both cases, the results show that SGGD can accelerate the training, improve the generalization ability, and remove vanishing gradients, especially when the training data is biased.
title Symmetry-guided gradient descent for quantum neural networks
topic Quantum Physics
url https://arxiv.org/abs/2404.06108