Quixer: A Quantum Transformer Model

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Khatri, Nikhil, Matos, Gabriel, Coopmans, Luuk, Clark, Stephen
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910475260788736
author Khatri, Nikhil
Matos, Gabriel
Coopmans, Luuk
Clark, Stephen
author_facet Khatri, Nikhil
Matos, Gabriel
Coopmans, Luuk
Clark, Stephen
contents Progress in the realisation of reliable large-scale quantum computers has motivated research into the design of quantum machine learning models. We present Quixer: a novel quantum transformer model which utilises the Linear Combination of Unitaries and Quantum Singular Value Transform primitives as building blocks. Quixer operates by preparing a superposition of tokens and applying a trainable non-linear transformation to this mix. We present the first results for a quantum transformer model applied to a practical language modelling task, obtaining results competitive with an equivalent classical baseline. In addition, we include resource estimates for evaluating the model on quantum hardware, and provide an open-source implementation for classical simulation. We conclude by highlighting the generality of Quixer, showing that its parameterised components can be substituted with fixed structures to yield new classes of quantum transformers.
format Preprint
id arxiv_https___arxiv_org_abs_2406_04305
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Quixer: A Quantum Transformer Model
Khatri, Nikhil
Matos, Gabriel
Coopmans, Luuk
Clark, Stephen
Quantum Physics
Progress in the realisation of reliable large-scale quantum computers has motivated research into the design of quantum machine learning models. We present Quixer: a novel quantum transformer model which utilises the Linear Combination of Unitaries and Quantum Singular Value Transform primitives as building blocks. Quixer operates by preparing a superposition of tokens and applying a trainable non-linear transformation to this mix. We present the first results for a quantum transformer model applied to a practical language modelling task, obtaining results competitive with an equivalent classical baseline. In addition, we include resource estimates for evaluating the model on quantum hardware, and provide an open-source implementation for classical simulation. We conclude by highlighting the generality of Quixer, showing that its parameterised components can be substituted with fixed structures to yield new classes of quantum transformers.
title Quixer: A Quantum Transformer Model
topic Quantum Physics
url https://arxiv.org/abs/2406.04305