Metraipolis › archive › dc_607769bc3ef7

Empirical Characterization of Learning Geometry in Hybrid Quantum Forecasting Models — arXiv:2608.19497

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.19497
License (as archived)
CC0-1.0
Archived
2026-10-18T11:48:08.782Z
SHA-256 of the archived text
58b07b2392c8d827b3171da190d6a4b05327711b4aeabf9355147c7ba0fd58d0
Stable URL of this page
https://metraipolis.com/documento/dc_607769bc3ef7

How to cite

Empirical Characterization of Learning Geometry in Hybrid Quantum Forecasting Models — arXiv:2608.19497 — arXiv (en), https://arxiv.org/abs/2608.19497 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_607769bc3ef7 (Metraipolis archive dc_607769bc3ef7, sha256 58b07b2392c8d827b3171da190d6a4b05327711b4aeabf9355147c7ba0fd58d0)
BibTeX
@misc{dc607769bc3ef7,
  title = {Empirical Characterization of Learning Geometry in Hybrid Quantum Forecasting Models — arXiv:2608.19497},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.19497},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_607769bc3ef7; sha256 58b07b2392c8d827b3171da190d6a4b05327711b4aeabf9355147c7ba0fd58d0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.19497. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We characterize the learning dynamics of a compact hybrid quantum forecasting model through comparison with a structurally aligned classical baseline. Using stationary harmonic-mixture and nonstationary chirp benchmarks with controlled spectral complexity and data availability, we analyze empirical Neural Tangent Kernel dynamics through kernel-target alignment, kernel drift, spectral concentration, and training loss. The classical model exhibits stronger early target alignment, whereas the hybrid model generally develops a less concentrated kernel spectrum and smaller kernel drift. Despite these distinct optimization geometries, both architectures attain similar held-out performance across the evaluated regimes. Notably, the hybrid model uses 125 trainable parameters compared with 281 for the classical baseline and reaches its validation-selected checkpoint earlier in 15 of 18 frequency conditions. A Fourier-augmented classical baseline does not reproduce the observed training behavior, while a controlled re-uploading ablation shows that repeated encoding systematically modifies both optimization and kernel geometry. These results demonstrate that comparable generalization can emerge from substantially different learning trajectories and that individual NTK diagnostics do not provide monotonic predictors of validation convergence. Rather than claiming a general quantum advantage, the study identifies architecture-dependent learning behavior that is masked by endpoint accuracy alone.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-21 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.19497 — 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 2026-10-18T11:47:43.300Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).