Prediction and real-time compensation of qubit decoherence via machine-learning

TL;DR

This paper introduces a machine learning-based method to predict and compensate for qubit decoherence in real-time, significantly enhancing quantum coherence stability without extra hardware, applicable to all two-level quantum systems.

Contribution

It presents a novel control strategy combining machine learning and control theory to predict qubit evolution and suppress decoherence during limited measurement access.

Findings

Improved qubit phase stability over traditional feedback methods

Effective decoherence suppression using predictive feedback

No additional hardware required for implementation

Abstract

The wide-ranging adoption of quantum technologies requires practical, high-performance advances in our ability to maintain quantum coherence while facing the challenge of state collapse under measurement. Here we use techniques from control theory and machine learning to predict the future evolution of a qubit's state; we deploy this information to suppress stochastic, semiclassical decoherence, even when access to measurements is limited. First, we implement a time-division-multiplexed approach, interleaving measurement periods with periods of unsupervised but stabilised operation during which qubits are available, for e.g. quantum information experiments. Second, we employ predictive feedback during sequential but time delayed measurements to reduce the Dick effect as encountered in passive frequency standards. Both experiments demonstrate significant improvements in qubit phase stability over "traditional" measurement-based feedback approaches by exploiting time domain correlations in the noise processes. This technique requires no additional hardware and is applicable to all two-level quantum systems where projective measurements are possible.