Shadows of quantum machine learning
This work addresses the practical barrier for widespread adoption of quantum machine learning by enabling classical deployment, potentially broadening its applicability in real-world scenarios, though it is incremental in focusing on deployment rather than training efficiency.
The paper tackles the problem that quantum machine learning models require quantum computers for both training and deployment, by introducing a class of models where quantum resources are only needed during training, enabling classical deployment; they prove these models are universal for classically-deployed quantum machine learning, have restricted capacities compared to fully quantum models, but achieve a provable learning advantage over classical learners under complexity theory assumptions.
Quantum machine learning is often highlighted as one of the most promising practical applications for which quantum computers could provide a computational advantage. However, a major obstacle to the widespread use of quantum machine learning models in practice is that these models, even once trained, still require access to a quantum computer in order to be evaluated on new data. To solve this issue, we introduce a new class of quantum models where quantum resources are only required during training, while the deployment of the trained model is classical. Specifically, the training phase of our models ends with the generation of a 'shadow model' from which the classical deployment becomes possible. We prove that: i) this class of models is universal for classically-deployed quantum machine learning; ii) it does have restricted learning capacities compared to 'fully quantum' models, but nonetheless iii) it achieves a provable learning advantage over fully classical learners, contingent on widely-believed assumptions in complexity theory. These results provide compelling evidence that quantum machine learning can confer learning advantages across a substantially broader range of scenarios, where quantum computers are exclusively employed during the training phase. By enabling classical deployment, our approach facilitates the implementation of quantum machine learning models in various practical contexts.