When Does Adaptation Win? Scaling Laws for Meta-Learning in Quantum Control

Nima Leclerc, Chris Miller, Nicholas Peter Brawand
Proceedings of the 43rd International Conference on Machine Learning, PMLR 306:63206-63238, 2026.

Abstract

Quantum hardware suffers from intrinsic device heterogeneity and environmental drift, forcing practitioners to choose between suboptimal non-adaptive controllers or costly per-device recalibration. We derive a scaling law lower bound for meta-learning showing that the adaptation gain (expected fidelity improvement from task-specific gradient steps) saturates exponentially with gradient steps and scales linearly with task variance, providing a quantitative criterion for when adaptation justifies its overhead. Validation on quantum gate calibration shows negligible benefits for low-variance tasks but $>$ 40% fidelity gains on two-qubit gates under extreme out-of-distribution conditions (10$\times$ the training noise), with implications for reducing per-device calibration time on cloud quantum processors. Further validation on classical linear-quadratic control confirms these laws emerge from general optimization geometry rather than quantum-specific physics. We further introduce a few-shot pre-adaptation protocol that estimates the optimal adaptation budget from $N =3–5$ probe steps within 3–19% relative error across out-of-distribution regimes.

Cite this Paper


BibTeX
@InProceedings{pmlr-v306-leclerc26a, title = {When Does Adaptation Win? {S}caling Laws for Meta-Learning in Quantum Control}, author = {Leclerc, Nima and Miller, Chris and Brawand, Nicholas Peter}, booktitle = {Proceedings of the 43rd International Conference on Machine Learning}, pages = {63206--63238}, year = {2026}, editor = {Zhang, Tong and Dudik, Miroslav and Jaggi, Martin and Agarwal, Alekh and Li, Sharon and Schuurmans, Dale and Zhu, Jerry and Berkenkamp, Felix and Dong, Hanze and Bietti, Alberto}, volume = {306}, series = {Proceedings of Machine Learning Research}, month = {06--11 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v306/main/assets/leclerc26a/leclerc26a.pdf}, url = {https://proceedings.mlr.press/v306/leclerc26a.html}, abstract = {Quantum hardware suffers from intrinsic device heterogeneity and environmental drift, forcing practitioners to choose between suboptimal non-adaptive controllers or costly per-device recalibration. We derive a scaling law lower bound for meta-learning showing that the adaptation gain (expected fidelity improvement from task-specific gradient steps) saturates exponentially with gradient steps and scales linearly with task variance, providing a quantitative criterion for when adaptation justifies its overhead. Validation on quantum gate calibration shows negligible benefits for low-variance tasks but $>$ 40% fidelity gains on two-qubit gates under extreme out-of-distribution conditions (10$\times$ the training noise), with implications for reducing per-device calibration time on cloud quantum processors. Further validation on classical linear-quadratic control confirms these laws emerge from general optimization geometry rather than quantum-specific physics. We further introduce a few-shot pre-adaptation protocol that estimates the optimal adaptation budget from $N =3–5$ probe steps within 3–19% relative error across out-of-distribution regimes.} }
Endnote
%0 Conference Paper %T When Does Adaptation Win? Scaling Laws for Meta-Learning in Quantum Control %A Nima Leclerc %A Chris Miller %A Nicholas Peter Brawand %B Proceedings of the 43rd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2026 %E Tong Zhang %E Miroslav Dudik %E Martin Jaggi %E Alekh Agarwal %E Sharon Li %E Dale Schuurmans %E Jerry Zhu %E Felix Berkenkamp %E Hanze Dong %E Alberto Bietti %F pmlr-v306-leclerc26a %I PMLR %P 63206--63238 %U https://proceedings.mlr.press/v306/leclerc26a.html %V 306 %X Quantum hardware suffers from intrinsic device heterogeneity and environmental drift, forcing practitioners to choose between suboptimal non-adaptive controllers or costly per-device recalibration. We derive a scaling law lower bound for meta-learning showing that the adaptation gain (expected fidelity improvement from task-specific gradient steps) saturates exponentially with gradient steps and scales linearly with task variance, providing a quantitative criterion for when adaptation justifies its overhead. Validation on quantum gate calibration shows negligible benefits for low-variance tasks but $>$ 40% fidelity gains on two-qubit gates under extreme out-of-distribution conditions (10$\times$ the training noise), with implications for reducing per-device calibration time on cloud quantum processors. Further validation on classical linear-quadratic control confirms these laws emerge from general optimization geometry rather than quantum-specific physics. We further introduce a few-shot pre-adaptation protocol that estimates the optimal adaptation budget from $N =3–5$ probe steps within 3–19% relative error across out-of-distribution regimes.
APA
Leclerc, N., Miller, C. & Brawand, N.P.. (2026). When Does Adaptation Win? Scaling Laws for Meta-Learning in Quantum Control. Proceedings of the 43rd International Conference on Machine Learning, in Proceedings of Machine Learning Research 306:63206-63238 Available from https://proceedings.mlr.press/v306/leclerc26a.html.

Related Material