The power of quantum neural networks
This work addresses the challenge of quantifying advantages in near-term quantum machine learning for researchers in quantum computing and AI, though it is incremental in establishing specific metrics rather than broad breakthroughs.
The authors tackled the problem of understanding expressibility and trainability in quantum neural networks by defining expressibility using information geometry and connecting it to generalization bounds and barren plateaus. They demonstrated that well-designed quantum neural networks achieve a higher effective dimension and faster training than classical models, verifying this on real quantum hardware.
Fault-tolerant quantum computers offer the promise of dramatically improving machine learning through speed-ups in computation or improved model scalability. In the near-term, however, the benefits of quantum machine learning are not so clear. Understanding expressibility and trainability of quantum models-and quantum neural networks in particular-requires further investigation. In this work, we use tools from information geometry to define a notion of expressibility for quantum and classical models. The effective dimension, which depends on the Fisher information, is used to prove a novel generalisation bound and establish a robust measure of expressibility. We show that quantum neural networks are able to achieve a significantly better effective dimension than comparable classical neural networks. To then assess the trainability of quantum models, we connect the Fisher information spectrum to barren plateaus, the problem of vanishing gradients. Importantly, certain quantum neural networks can show resilience to this phenomenon and train faster than classical models due to their favourable optimisation landscapes, captured by a more evenly spread Fisher information spectrum. Our work is the first to demonstrate that well-designed quantum neural networks offer an advantage over classical neural networks through a higher effective dimension and faster training ability, which we verify on real quantum hardware.