Data-Driven Hamiltonian Reduction for Superconducting Qubits via Meta-Learning

TL;DR

HAML is a meta-learning framework enabling rapid online adaptation of effective Hamiltonian models for superconducting qubits, improving calibration and control without relying on perturbation theory.

Contribution

It introduces a data-driven, scalable method for Hamiltonian reduction and characterization that works even when traditional perturbation methods fail.

Findings

Successfully recovers effective two-qubit coefficients across various regimes.

Outperforms perturbation theory in parameter regions where SWPT breaks down.

Uses variance-maximizing measurement selection to enhance adaptation efficiency.

Abstract

We introduce HAML (Hamiltonian Adaptation via Meta-Learning), a framework for fast online adaptation of effective Hamiltonian models of superconducting quantum processors. HAML proceeds in two phases. A supervised training phase uses an ensemble of simulated devices to learn an offline map from control inputs and device parameters to effective Hamiltonian coefficients. An online adaptation phase then uses a small number of hardware-accessible measurements to identify the unknown parameters of a new device. By training directly against effective two-qubit coefficients extracted from full multi-mode simulations, HAML implicitly learns the reduction from full multi-mode Hamiltonians to effective qubit descriptions without invoking perturbation theory. We further show that a variance-maximizing greedy selection of measurement configurations boosts online adaptation efficiency. We demonstrate HAML on a transmon-coupler-transmon system, recovering effective two-qubit coefficients across a wide range of operating regimes, including parameter regions where Schrieffer-Wolff perturbation theory (SWPT) breaks down. This establishes a scalable, sample-efficient approach to Hamiltonian reduction and characterization for near-term quantum processors, with direct implications for calibration, control, and error mitigation.