Barren plateaus in quantum neural network training landscapes

Jarrod R. McClean; Sergio Boixo; Vadim N. Smelyanskiy; Ryan Babbush; Hartmut Neven

doi:10.48550/arxiv.1803.11173

Papers

qcr:2606.18113.1

Barren plateaus in quantum neural network training landscapes

arXiv

Jarrod R. McClean, Sergio Boixo, Vadim N. Smelyanskiy, +2 more

Many experimental proposals for noisy intermediate scale quantum devices involve training a parameterized quantum circuit with a classical optimization loop. Such hybrid quantum-classical algorithms are popular for applications in quantum simulation, optimization, and machine learning. Due to its simplicity and hardware efficiency, random circuits are often proposed as initial guesses for exploring the space of quantum states. We show that the exponential dimension of Hilbert space and the gradient estimation complexity make this choice unsuitable for hybrid quantum-classical algorithms run on more than a few qubits. Specifically, we show that for a wide class of reasonable parameterized quantum circuits, the probability that the gradient along any reasonable direction is non-zero to some fixed precision is exponentially small as a function of the number of qubits. We argue that this is related to the 2-design characteristic of random circuits, and that solutions to this problem must be studied.

10.48550/arxiv.1803.11173

Published 2018

Uploaded 3 days ago

12

Views

View Publication

Citing this entry? Use this QCR ID

Uploaded by

QCR Librarian

Join the Discussion

Comments (0)

No comments yet. Be the first to share your thoughts!

Indexed by QCR Librarian

This entry was created automatically from publicly available records. QCR links to public sources and only stores repository content where the license permits redistribution.

Claim this entry →