Leveraging Machine Learning to Overcome Limitations in Quantum Algorithms

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sala, Laia Coronas, Atchade-Adelemou, Parfait
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929632632111104
author Sala, Laia Coronas
Atchade-Adelemou, Parfait
author_facet Sala, Laia Coronas
Atchade-Adelemou, Parfait
contents Quantum Computing (QC) offers outstanding potential for molecular characterization and drug discovery, particularly in solving complex properties like the Ground State Energy (GSE) of biomolecules. However, QC faces challenges due to computational noise, scalability, and system complexity. This work presents a hybrid framework combining Machine Learning (ML) techniques with quantum algorithms$-$Variational Quantum Eigensolver (VQE), Hartree-Fock (HF), and Quantum Phase Estimation (QPE)$-$to improve GSE predictions for large molecules. Three datasets (chemical descriptors, Coulomb matrices, and a hybrid combination) were prepared using molecular features from PubChem. These datasets trained XGBoost (XGB), Random Forest (RF), and LightGBM (LGBM) models. XGB achieved the lowest Relative Error (RE) of $4.41 \pm 11.18\%$ on chemical descriptors, outperforming RF ($5.56 \pm 11.66\%$) and LGBM ($5.32 \pm 12.87\%$). HF delivered exceptional precision for small molecules ($0.44 \pm 0.66\% RE$), while a near-linear correlation between GSE and molecular electron count provided predictive shortcuts. This study demonstrates that integrating QC and ML enhances scalability for molecular energy predictions and lays the foundation for scaling QC molecular simulations to larger systems.
format Preprint
id arxiv_https___arxiv_org_abs_2412_11405
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Leveraging Machine Learning to Overcome Limitations in Quantum Algorithms
Sala, Laia Coronas
Atchade-Adelemou, Parfait
Chemical Physics
Quantum Physics
Quantum Computing (QC) offers outstanding potential for molecular characterization and drug discovery, particularly in solving complex properties like the Ground State Energy (GSE) of biomolecules. However, QC faces challenges due to computational noise, scalability, and system complexity. This work presents a hybrid framework combining Machine Learning (ML) techniques with quantum algorithms$-$Variational Quantum Eigensolver (VQE), Hartree-Fock (HF), and Quantum Phase Estimation (QPE)$-$to improve GSE predictions for large molecules. Three datasets (chemical descriptors, Coulomb matrices, and a hybrid combination) were prepared using molecular features from PubChem. These datasets trained XGBoost (XGB), Random Forest (RF), and LightGBM (LGBM) models. XGB achieved the lowest Relative Error (RE) of $4.41 \pm 11.18\%$ on chemical descriptors, outperforming RF ($5.56 \pm 11.66\%$) and LGBM ($5.32 \pm 12.87\%$). HF delivered exceptional precision for small molecules ($0.44 \pm 0.66\% RE$), while a near-linear correlation between GSE and molecular electron count provided predictive shortcuts. This study demonstrates that integrating QC and ML enhances scalability for molecular energy predictions and lays the foundation for scaling QC molecular simulations to larger systems.
title Leveraging Machine Learning to Overcome Limitations in Quantum Algorithms
topic Chemical Physics
Quantum Physics
url https://arxiv.org/abs/2412.11405