Improvise, Adapt, Overcome: An On-The-Fly Multifidelity Algorithm for Efficient Machine Learning
Abstract
Machine learning has accelerated quantum chemistry but is hindered by the prohibitive cost of generating high fidelity training data. Multifidelity machine learning (MFML) mitigates this overhead by systematically combining abundant low fidelity data with sparse high fidelity data. In spite of its success, standard MFML schemes rely on pre-defined scaling factors to determine sparse data ratio across fidelities, often generating redundant multifidelity data resulting in a loss of efficiency. Here, we introduce an adaptive on-the-fly multifidelity framework for machine learning that autonomously determines training dataset composition. By dynamically querying training samples at each fidelity, the algorithm saturates model accuracy at lower fidelities before moving up to more expensive reference calculations. We benchmark the novel adaptive-MFML across diverse chemical properties including theoretical best estimate ab initio potential energy surfaces, golden standard coupled cluster energies, and the more chemically challenging excitation energies. In our numerical experiments we show that our adaptive algorithm reduces data generation costs by up to a factor of 20 compared to single fidelity methods and improves upon standard MFML by up to a factor of 3. The mitigation of data redundancy establishes a high-accuracy low-cost pathway for sustainable cost-aware machine learning in quantum chemistry.
Related
- Embedded Morgan Fingerprints for more efficient molecular property predictions with machine learning
- Chemistry-Informed Transfer and Interaction-Resolved Learning Towards Data-Efficient Materials Exploration
- Fast State-of-Health Estimation of Lithium-Ion Batteries Using Short-Term Relaxation-Voltage Features Integrated with a Differential Evolution-Optimized Extreme Learning Machine Algorithm
- Data-Efficient Machine Learning Potentials for Organic Reactions through Active-Learning-Guided Fine-Tuning
- Efficient and Transferable Machine Learning Potentials for Zn-Coordinated Zeolitic Imidazolate Frameworks Through Structural Diversity Sampling and Transfer Learning.
BibTeX
@misc{vinod2026improvise,
title = {{Improvise, Adapt, Overcome: An On-The-Fly Multifidelity Algorithm for Efficient Machine Learning}},
author = {Vivin Vinod and Peter Zaspel},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2606.02662},
eprint = {2606.02662},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2606.02662},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Improvise, Adapt, Overcome: An On-The-Fly Multifidelity Algorithm for Efficient Machine Learning
AU - Vivin Vinod
AU - Peter Zaspel
PY - 2026
DA - 2026/10/31
PB - arXiv
DO - 10.48550/arxiv.2606.02662
UR - https://arxiv.org/abs/2606.02662
AB - Machine learning has accelerated quantum chemistry but is hindered by the prohibitive cost of generating high fidelity training data. Multifidelity machine learning (MFML) mitigates this overhead by systematically combining abundant low fidelity data with sparse high fidelity data. In spite of its success, standard MFML schemes rely on pre-defined scaling factors to determine sparse data ratio across fidelities, often generating redundant multifidelity data resulting in a loss of efficiency. Here, we introduce an adaptive on-the-fly multifidelity framework for machine learning that autonomously determines training dataset composition. By dynamically querying training samples at each fidelity, the algorithm saturates model accuracy at lower fidelities before moving up to more expensive reference calculations. We benchmark the novel adaptive-MFML across diverse chemical properties including theoretical best estimate ab initio potential energy surfaces, golden standard coupled cluster energies, and the more chemically challenging excitation energies. In our numerical experiments we show that our adaptive algorithm reduces data generation costs by up to a factor of 20 compared to single fidelity methods and improves upon standard MFML by up to a factor of 3. The mitigation of data redundancy establishes a high-accuracy low-cost pathway for sustainable cost-aware machine learning in quantum chemistry.
ER -