For adversarially trained quantum classifiers, the excess sample complexity over standard training vanishes with input dimension for rotation embeddings under classical attacks, scales at least linearly for amplitude embeddings, and depends only on Hilbert space dimension under quantum attacks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
quant-ph 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
On the Generalization of Adversarially Trained Quantum Classifiers
For adversarially trained quantum classifiers, the excess sample complexity over standard training vanishes with input dimension for rotation embeddings under classical attacks, scales at least linearly for amplitude embeddings, and depends only on Hilbert space dimension under quantum attacks.