Quantum sequel of neural network training
arXiv:2506.05244 · doi:10.1038/s42005-025-02384-8
Abstract
Training of neural networks (NNs) has emerged as a major consumer of both computational and energy resources. Quantum computers were coined as a root to facilitate training, but no experimental evidence has been presented so far. Here we demonstrate that quantum annealing platforms, such as D-Wave, can enable fast and efficient training of classical NNs, which are then deployable on conventional hardware. From a physics perspective, NN training can be viewed as a dynamical phase transition: the system evolves from an initial spin glass state to a highly ordered, trained state. This process involves eliminating numerous undesired minima in its energy landscape. The advantage of annealing devices is their ability to rapidly find multiple deep states. We found that this quantum training achieves superior performance scaling compared to classical backpropagation methods, with a clearly higher scaling exponent (1.01 vs. 0.78). It may be further increased up to a factor of 2 with a fully coherent quantum platform using a variant of the Grover algorithm. Furthermore, we argue that even a modestly sized annealer can be beneficial to train a deep NN by being applied sequentially to a few layers at a time.
6 pages, 5 figures
References in corpus (17)
- Quantum Machine Learning
- Barren plateaus in quantum neural network training landscapes
- A Quantum Adiabatic Evolution Algorithm Applied to Random Instances of an NP-Complete Problem
- Logical quantum processor based on reconfigurable atom arrays
- Theory of Quantum Annealing of an Ising Spin Glass
- Quantum error correction below the surface code threshold
- Quantum generative adversarial learning
- Coherent quantum annealing in a programmable 2000-qubit Ising chain
- Beyond-classical computation in quantum simulation
- Training and Classification using a Restricted Boltzmann Machine on the D-Wave 2000Q
- Realization of quantum signal processing on a noisy quantum computer
- The Quantum Transition of the Two-Dimensional Ising Spin Glass: A Tale of Two Gaps
- Scaling Advantage in Approximate Optimization with Quantum Annealing
- Many-body localization enables iterative quantum optimization
- Cyclic Quantum Annealing: Searching for Deep Low-Energy States in 5000-Qubit Spin Glass
- Computational complexity of three-dimensional Ising spin glass: Lessons from D-Wave annealer
- Amplitude Amplification and Estimation using a Floquet system