Saved in:
Bibliographic Details
Main Authors: Carrasquilla, Juan, Hibat-Allah, Mohamed, Inack, Estelle, Makhzani, Alireza, Neklyudov, Kirill, Taylor, Graham W., Torlai, Giacomo
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2301.08292
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913945077415936
author Carrasquilla, Juan
Hibat-Allah, Mohamed
Inack, Estelle
Makhzani, Alireza
Neklyudov, Kirill
Taylor, Graham W.
Torlai, Giacomo
author_facet Carrasquilla, Juan
Hibat-Allah, Mohamed
Inack, Estelle
Makhzani, Alireza
Neklyudov, Kirill
Taylor, Graham W.
Torlai, Giacomo
contents Binary neural networks, i.e., neural networks whose parameters and activations are constrained to only two possible values, offer a compelling avenue for the deployment of deep learning models on energy- and memory-limited devices. However, their training, architectural design, and hyperparameter tuning remain challenging as these involve multiple computationally expensive combinatorial optimization problems. Here we introduce quantum hypernetworks as a mechanism to train binary neural networks on quantum computers, which unify the search over parameters, hyperparameters, and architectures in a single optimization loop. Through classical simulations, we demonstrate that our approach effectively finds optimal parameters, hyperparameters and architectural choices with high probability on classification problems including a two-dimensional Gaussian dataset and a scaled-down version of the MNIST handwritten digits. We represent our quantum hypernetworks as variational quantum circuits, and find that an optimal circuit depth maximizes the probability of finding performant binary neural networks. Our unified approach provides an immense scope for other applications in the field of machine learning.
format Preprint
id arxiv_https___arxiv_org_abs_2301_08292
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Quantum HyperNetworks: Training Binary Neural Networks in Quantum Superposition
Carrasquilla, Juan
Hibat-Allah, Mohamed
Inack, Estelle
Makhzani, Alireza
Neklyudov, Kirill
Taylor, Graham W.
Torlai, Giacomo
Quantum Physics
Machine Learning
Binary neural networks, i.e., neural networks whose parameters and activations are constrained to only two possible values, offer a compelling avenue for the deployment of deep learning models on energy- and memory-limited devices. However, their training, architectural design, and hyperparameter tuning remain challenging as these involve multiple computationally expensive combinatorial optimization problems. Here we introduce quantum hypernetworks as a mechanism to train binary neural networks on quantum computers, which unify the search over parameters, hyperparameters, and architectures in a single optimization loop. Through classical simulations, we demonstrate that our approach effectively finds optimal parameters, hyperparameters and architectural choices with high probability on classification problems including a two-dimensional Gaussian dataset and a scaled-down version of the MNIST handwritten digits. We represent our quantum hypernetworks as variational quantum circuits, and find that an optimal circuit depth maximizes the probability of finding performant binary neural networks. Our unified approach provides an immense scope for other applications in the field of machine learning.
title Quantum HyperNetworks: Training Binary Neural Networks in Quantum Superposition
topic Quantum Physics
Machine Learning
url https://arxiv.org/abs/2301.08292