Understanding Generalization in Quantum Machine Learning with Margins

Tak Hur, Daniel K. Park
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:26338-26360, 2025.

Abstract

Understanding and improving generalization capabilities is crucial for both classical and quantum machine learning (QML). Recent studies have revealed shortcomings in current generalization theories, particularly those relying on uniform bounds, across both classical and quantum settings. In this work, we present a margin-based generalization bound for QML models, providing a more reliable framework for evaluating generalization. Our experimental studies on the quantum phase recognition dataset demonstrate that margin-based metrics are strong predictors of generalization performance, outperforming traditional metrics like parameter count. By connecting this margin-based metric to quantum information theory, we demonstrate how to enhance the generalization performance of QML through a classical-quantum hybrid approach when applied to classical data.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-hur25a, title = {Understanding Generalization in Quantum Machine Learning with Margins}, author = {Hur, Tak and Park, Daniel K.}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {26338--26360}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/hur25a/hur25a.pdf}, url = {https://proceedings.mlr.press/v267/hur25a.html}, abstract = {Understanding and improving generalization capabilities is crucial for both classical and quantum machine learning (QML). Recent studies have revealed shortcomings in current generalization theories, particularly those relying on uniform bounds, across both classical and quantum settings. In this work, we present a margin-based generalization bound for QML models, providing a more reliable framework for evaluating generalization. Our experimental studies on the quantum phase recognition dataset demonstrate that margin-based metrics are strong predictors of generalization performance, outperforming traditional metrics like parameter count. By connecting this margin-based metric to quantum information theory, we demonstrate how to enhance the generalization performance of QML through a classical-quantum hybrid approach when applied to classical data.} }
Endnote
%0 Conference Paper %T Understanding Generalization in Quantum Machine Learning with Margins %A Tak Hur %A Daniel K. Park %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-hur25a %I PMLR %P 26338--26360 %U https://proceedings.mlr.press/v267/hur25a.html %V 267 %X Understanding and improving generalization capabilities is crucial for both classical and quantum machine learning (QML). Recent studies have revealed shortcomings in current generalization theories, particularly those relying on uniform bounds, across both classical and quantum settings. In this work, we present a margin-based generalization bound for QML models, providing a more reliable framework for evaluating generalization. Our experimental studies on the quantum phase recognition dataset demonstrate that margin-based metrics are strong predictors of generalization performance, outperforming traditional metrics like parameter count. By connecting this margin-based metric to quantum information theory, we demonstrate how to enhance the generalization performance of QML through a classical-quantum hybrid approach when applied to classical data.
APA
Hur, T. & Park, D.K.. (2025). Understanding Generalization in Quantum Machine Learning with Margins. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:26338-26360 Available from https://proceedings.mlr.press/v267/hur25a.html.

Related Material