Metraipolis › archive › dc_bf6c447c4397

Unflattening by Flattening -- How Input Distributions Shape Output Variance in Angle-Encoded Circuits — arXiv:2610.01446

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.01446
License (as archived)
CC0-1.0
Archived
2026-10-07T11:37:49.558Z
SHA-256 of the archived text
08aed9d9b86e1d2fd213913fdb6db28d3f35d2ccdbe9e4772403613feac57216
Stable URL of this page
https://metraipolis.com/documento/dc_bf6c447c4397

How to cite

Unflattening by Flattening -- How Input Distributions Shape Output Variance in Angle-Encoded Circuits — arXiv:2610.01446 — arXiv (en), https://arxiv.org/abs/2610.01446 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bf6c447c4397 (Metraipolis archive dc_bf6c447c4397, sha256 08aed9d9b86e1d2fd213913fdb6db28d3f35d2ccdbe9e4772403613feac57216)
BibTeX
@misc{dcbf6c447c4397,
  title = {Unflattening by Flattening -- How Input Distributions Shape Output Variance in Angle-Encoded Circuits — arXiv:2610.01446},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.01446},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bf6c447c4397; sha256 08aed9d9b86e1d2fd213913fdb6db28d3f35d2ccdbe9e4772403613feac57216},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.01446. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Barren plateaus hinder training of parameterized quantum circuits by making loss gradients exponentially small in the number of qubits. For angle-encoded product states, we show how the input distribution affects output variation through algebraic input purity, i.e. the input's overlap with the circuit's dynamical Lie algebra. With the specified readouts and Haar or exact group 2-design sampling, matchgate circuits on $n$ qubits retain output variance of order $1/n$ for every pure product input. The off-diagonal family instead has zero output on computational-basis inputs at any depth and for every parameter choice. Independent uniform angles yield mean variance of the same order as matchgates. A count of diagonal Pauli strings identifies these zero-output endpoints. For any fixed dataset of nonzero inputs with at least $2n$ coordinates, we construct a classical preprocessing certificate. A shared random rotation is accepted only when the dataset's mean purity passes a computable threshold. This certifies mean output variance of order $1/n$ for the off-diagonal family before circuit execution, with a constant expected number of trials. Binary and ternary weighted encodings also recover the independent-angle mean purity from one uniform scalar input. Numerical experiments examine training behavior and extensions to larger algebras. The guarantee concerns output variance averaged over inputs, while successful learning also depends on the task and information preserved by the encoding.

Tema degli esploratori: fisica e astronomia (retro-catalogo arXiv: annunci del 2026-10-02 in quant-ph).
Categorie arXiv: Quantum Physics (quant-ph).
Pagina del lavoro: https://arxiv.org/abs/2610.01446 — 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 2026-10-07T11:19:01.689Z dalla pagina https://arxiv.org/catchup/quant-ph/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).