Adversaries perturbing shared entanglement in distributed VQAs can manipulate a new Kraus expressibility metric to keep gradients large but steer training to incorrect solutions.
arXiv preprint arXiv:2106.12819 (2021)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
quant-ph 2verdicts
UNVERDICTED 2representative citing papers
Distributed QNNs with partitioned feature encoding achieve >96% accuracy on MNIST 10-class classification using ensembles of small circuits.
citing papers explorer
-
Adversarial Effects on Expressibility and Trainability in Distributed Variational Quantum Algorithms
Adversaries perturbing shared entanglement in distributed VQAs can manipulate a new Kraus expressibility metric to keep gradients large but steer training to incorrect solutions.
-
Distributed Quantum Neural Networks via Partitioned Features Encoding
Distributed QNNs with partitioned feature encoding achieve >96% accuracy on MNIST 10-class classification using ensembles of small circuits.