Metraipolis › archive › dc_c19c906404cb

When Does Interference Help Learning? Kernel Geometry as a Pre-Experimental Test for Photonic Reservoir Computing — arXiv:2610.11360

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.11360
License (as archived): CC0-1.0
Archived: 2026-10-09T06:39:04.091Z
SHA-256 of the archived text: 3f32c6da7cf4daa52a9c8cd7cbdfd110257dc41211812f92a2064ab8e44bd246
Stable URL of this page: https://metraipolis.com/documento/dc_c19c906404cb

How to cite

When Does Interference Help Learning? Kernel Geometry as a Pre-Experimental Test for Photonic Reservoir Computing — arXiv:2610.11360 — arXiv (en), https://arxiv.org/abs/2610.11360 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c19c906404cb (Metraipolis archive dc_c19c906404cb, sha256 3f32c6da7cf4daa52a9c8cd7cbdfd110257dc41211812f92a2064ab8e44bd246)

BibTeX

@misc{dcc19c906404cb,
  title = {When Does Interference Help Learning? Kernel Geometry as a Pre-Experimental Test for Photonic Reservoir Computing — arXiv:2610.11360},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.11360},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c19c906404cb; sha256 3f32c6da7cf4daa52a9c8cd7cbdfd110257dc41211812f92a2064ab8e44bd246},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.11360. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Multi-photon interference is the resource most native to photonic quantum machine learning, yet experiments on photonic reservoirs have reported advantages, null results, and train-only effects. These outcomes cannot be compared: each measures task-dependent accuracy on different tasks and platforms. Here we resolve the question task-independently through the kernel geometry of boson-sampling feature maps. Interference redistributes feature variance across roughly twice as many effective dimensions as distinguishable-particle statistics, generating a large geometric separation between the corresponding kernels. The separation grows superlinearly with indistinguishability, is linear in Hong--Ou--Mandel visibility at small visibility for two to four photons, and retains approximately 80% of its magnitude at the source quality of current quantum processors. Under experimental sampling budgets the separation is learnable on adversarially constructed tasks (accuracy advantage +0.22 plus or minus 0.05) and an order of magnitude smaller on natural tasks, gated by kernel--task alignment. The results reconcile the existing experimental record and supply a pre-experimental protocol: kernel geometry establishes that an interference-specific learning resource exists, and task alignment determines whether a given task can access it; both are computable before committing significant hardware resources.

Tema degli esploratori: fisica e astronomia (elenco arXiv quant-ph, nuovi lavori del giorno).
Categorie arXiv: Quantum Physics (quant-ph) ; Computational Engineering, Finance, and Science (cs.CE).
Pagina del lavoro: https://arxiv.org/abs/2610.11360 — 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 2026-10-09T05:58:46.890Z dalla pagina https://arxiv.org/list/quant-ph/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).