Researchers unravel quantum machine learning

A group of international researchers have discovered a major obstacle preventing quantum machine learning: too much quantum entanglement.

Quantum machine learning studies the benefits of quantum computers for artificial intelligence (AI). The hope is that in the future, quantum neural networks will be able to combine the strengths of quantum computing and traditional neural networks. However, recent theoretical research indicates potential difficulties.

Machine learning requires algorithms to learn from data in a phase called learning. During training, the algorithm gradually improves in the given task. However, it is mathematically proven that a large class of quantum algorithms experiences only negligible improvement due to a phenomenon known as a sterile plateau, first reported by a team at Google in 2018. L The experience of a sterile plateau may prevent the quantum algorithm from learning.

Theoretical research, published in Quantum PRX, studies the causes of arid plateaus in more detail, with an emphasis on the impact of excessive entanglement. The entanglement of qubits – or quantum bits – is a quantum effect that allows the exponential acceleration of quantum computing power.

“Although entanglement is necessary for quantum accelerations, research indicates the need for careful design of which qubits are to be entangled and their quantity,” says research co-author Dr Maria Kieferova, researcher at the ARC Center for Quantum Computing and Communication Technologies based at the Sydney University of Technology.

“This contradicts the commonly held idea that greater quantum entanglement provides faster accelerations. “

“We have proven that excessive entanglement between the output qubits, or visible units, and the rest of the quantum neural network hinders the learning process and that large amounts of entanglement can be catastrophic for the model,” explains lead author Dr. Carlos Ortiz Marrero, who is currently an assistant research professor at North Carolina State University.

“This result teaches us what structures of quantum neural networks we must avoid for successful algorithms.”

“Even though research has shown that a range of simple translations of classic machine learning models to the quantum domain is not beneficial, there is a way forward,” says Dr Ortiz Marrero.

“By limiting the depth and connectivity of the network, we might be able to avoid regimes where quantum machine learning algorithms cannot be trained.”

This can be achieved by precisely and deliberately deploying entanglement in quantum machine learning models.

“While entanglement is a powerful tool to add to our models, it should be used as a scalpel and not as a sledgehammer,” says co-author Dr. Nathan Wiebe, University of Toronto.

Disclaimer: AAAS and EurekAlert! are not responsible for the accuracy of any press releases posted on EurekAlert! by contributing institutions or for the use of any information via the EurekAlert system.