Image Classification with Rotation-Invariant Variational Quantum Circuits
This work addresses a specific bottleneck in quantum machine learning for researchers, but it is incremental as it builds on existing geometric methods.
The paper tackled the problem of barren plateaus in variational quantum algorithms by introducing an equivariant architecture for quantum classifiers with C4 rotational label symmetry, and experimentally observed that this geometric approach boosted performance in image classification tasks.
Variational quantum algorithms are gaining attention as an early application of Noisy Intermediate-Scale Quantum (NISQ) devices. One of the main problems of variational methods lies in the phenomenon of Barren Plateaus, present in the optimization of variational parameters. Adding geometric inductive bias to the quantum models has been proposed as a potential solution to mitigate this problem, leading to a new field called Geometric Quantum Machine Learning. In this work, an equivariant architecture for variational quantum classifiers is introduced to create a label-invariant model for image classification with $C_4$ rotational label symmetry. The equivariant circuit is benchmarked against two different architectures, and it is experimentally observed that the geometric approach boosts the model's performance. Finally, a classical equivariant convolution operation is proposed to extend the quantum model for the processing of larger images, employing the resources available in NISQ devices.