Metraipolis › archive › dc_37d8a22dab2e

A Quantum-Inspired Dequantization Method for Diagonally Weighted Matrix Functions: Application to Learning with Optimized Random Features — arXiv:2609.10729

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.10729
License (as archived)
CC0-1.0
Archived
2026-10-16T05:55:09.126Z
SHA-256 of the archived text
cac12b5e5cebae9e314af3699f1c7c24a443713a35ff5e1b48b6e7ef9cd07028
Stable URL of this page
https://metraipolis.com/documento/dc_37d8a22dab2e

How to cite

A Quantum-Inspired Dequantization Method for Diagonally Weighted Matrix Functions: Application to Learning with Optimized Random Features — arXiv:2609.10729 — arXiv (en), https://arxiv.org/abs/2609.10729 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_37d8a22dab2e (Metraipolis archive dc_37d8a22dab2e, sha256 cac12b5e5cebae9e314af3699f1c7c24a443713a35ff5e1b48b6e7ef9cd07028)
BibTeX
@misc{dc37d8a22dab2e,
  title = {A Quantum-Inspired Dequantization Method for Diagonally Weighted Matrix Functions: Application to Learning with Optimized Random Features — arXiv:2609.10729},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.10729},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_37d8a22dab2e; sha256 cac12b5e5cebae9e314af3699f1c7c24a443713a35ff5e1b48b6e7ef9cd07028},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.10729. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Quantum-inspired classical algorithms have dequantized several quantum machine learning routines by replacing quantum linear-algebra subroutines with classical counterparts. However, the sampler based on quantum singular value transformation (QSVT) for learning with optimized random features is not covered by existing dequantization frameworks, because the matrix to be inverted is not itself available through sampling access. In this work, we develop a classical algorithm to address this type of quantum-advantage candidate. Our method samples heavy indices, reduces the transformation to a small principal block, and outputs a sparse classical representation with operator-norm guarantees. Applying this method dequantizes the sampler for optimized random features, giving a classical sampler with prescribed accuracy and polynomially related runtime. These results show that the factorization underlying a quantum block encoding can itself provide sufficient classical structure even when sampling-and-query access to the composite matrix is unavailable.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-11 in cs.LG).
Categorie arXiv: Quantum Physics (quant-ph) ; Machine Learning (cs.LG); Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2609.10729 — 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 2026-10-16T05:44:25.039Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).