Absence of Barren Plateaus in Quantum Convolutional Neural Networks

Arthur Pesah, M. Cerezo, Samson Wang, Tyler Volkoff, Andrew T. Sornborger, Patrick J. Coles

Research output: Contribution to journalArticlepeer-review

140 Scopus citations


Quantum neural networks (QNNs) have generated excitement around the possibility of efficiently analyzing quantum data. But this excitement has been tempered by the existence of exponentially vanishing gradients, known as barren plateau landscapes, for many QNN architectures. Recently, quantum convolutional neural networks (QCNNs) have been proposed, involving a sequence of convolutional and pooling layers that reduce the number of qubits while preserving information about relevant data features. In this work, we rigorously analyze the gradient scaling for the parameters in the QCNN architecture. We find that the variance of the gradient vanishes no faster than polynomially, implying that QCNNs do not exhibit barren plateaus. This result provides an analytical guarantee for the trainability of randomly initialized QCNNs, which highlights QCNNs as being trainable under random initialization unlike many other QNN architectures. To derive our results, we introduce a novel graph-based method to analyze expectation values over Haar-distributed unitaries, which will likely be useful in other contexts. Finally, we perform numerical simulations to verify our analytical results.

Original languageEnglish
Article number041011
JournalPhysical Review X
Issue number4
StatePublished - Dec 2021
Externally publishedYes


Dive into the research topics of 'Absence of Barren Plateaus in Quantum Convolutional Neural Networks'. Together they form a unique fingerprint.

Cite this