Metraipolis › archive › dc_22eead1808f5

Overcoming the Representational Limitations of Amplitude Encoding for Quantum Neural Networks — arXiv:2610.41824

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.41824
License (as archived)
CC0-1.0
Archived
2026-11-03T08:13:27.568Z
SHA-256 of the archived text
d2096b099a399ea5617233fc2117297caab8e17a54b0475de0e6048787239890
Stable URL of this page
https://metraipolis.com/documento/dc_22eead1808f5

How to cite

Overcoming the Representational Limitations of Amplitude Encoding for Quantum Neural Networks — arXiv:2610.41824 — arXiv (en), https://arxiv.org/abs/2610.41824 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_22eead1808f5 (Metraipolis archive dc_22eead1808f5, sha256 d2096b099a399ea5617233fc2117297caab8e17a54b0475de0e6048787239890)
BibTeX
@misc{dc22eead1808f5,
  title = {Overcoming the Representational Limitations of Amplitude Encoding for Quantum Neural Networks — arXiv:2610.41824},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41824},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_22eead1808f5; sha256 d2096b099a399ea5617233fc2117297caab8e17a54b0475de0e6048787239890},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41824. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Quantum Neural Networks (QNNs) offer a framework for learning functions from classical data, but their expressive power depends critically on how inputs are encoded into quantum states. Angle encoding can require resources that scale with the number of features, whereas amplitude encoding represents $d$ features using only $\mathcal{O}(\log_2 d)$ qubits. This compactness comes at a representational cost: normalization makes conventional amplitude encoding invariant to nonzero real rescaling of the input, up to an unobservable global phase. We show that this invariance induces an exact, architecture-independent restriction on the resulting hypothesis class. No downstream quantum circuit can distinguish inputs differing by nonzero real scaling. We develop a general condition under which deterministic preprocessing can remove this ambiguity and show that nonlinearity alone is insufficient. Based on this analysis, we introduce a fixed nonlinear feature map that provably distinguishes all real inputs under subsequent amplitude encoding, without adding trainable parameters and while retaining logarithmic qubit scaling. We evaluate the resulting QNN on three canonical classification benchmarks and a nonlinear synthetic dataset against conventional amplitude and angle encoding, as well as a classical neural network. Across these tasks, the proposed encoding consistently improves classification accuracy over both quantum encoding baselines by 21$-$44 %. Our results establish normalization-induced scale invariance as a concrete representational bottleneck of amplitude encoding and demonstrate that it can be removed while preserving a compact quantum representation, marking a step toward quantum models capable of capturing arbitrary relationships in classical data.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Quantum Physics (quant-ph) ; Emerging Technologies (cs.ET); Machine Learning (cs.LG); Optimization and Control (math.OC).
Pagina del lavoro: https://arxiv.org/abs/2610.41824 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-03T08:02:38.995Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).