Metraipolis › archive › dc_cae866c032d2

Online Supervised Dimension Reduction with Random Features: Diagnostics and Computational Trade-offs — arXiv:2609.20454

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.20454
License (as archived): CC0-1.0
Archived: 2026-10-10T04:09:25.200Z
SHA-256 of the archived text: 239384c87cb0080336c3a25ce51a7bf22b91c0da6e24de11f43f6ccf42feb83c
Stable URL of this page: https://metraipolis.com/documento/dc_cae866c032d2

How to cite

Online Supervised Dimension Reduction with Random Features: Diagnostics and Computational Trade-offs — arXiv:2609.20454 — arXiv (en), https://arxiv.org/abs/2609.20454 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cae866c032d2 (Metraipolis archive dc_cae866c032d2, sha256 239384c87cb0080336c3a25ce51a7bf22b91c0da6e24de11f43f6ccf42feb83c)

BibTeX

@misc{dccae866c032d2,
  title = {Online Supervised Dimension Reduction with Random Features: Diagnostics and Computational Trade-offs — arXiv:2609.20454},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.20454},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cae866c032d2; sha256 239384c87cb0080336c3a25ce51a7bf22b91c0da6e24de11f43f6ccf42feb83c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.20454. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Accurate optimization of a supervised spectral objective need not produce an accurate population subspace or a better predictive representation. We investigate these distinctions for Online Kernel Supervised Principal Component Analysis (OKSPCA), which combines a centered cross-moment in finite random-feature coordinates with an Adam-style orthonormal basis update for an established objective. Fixed-map consistency, concentration and perturbation results describe the estimator and its exact subspace; same-target comparisons then assess the practical iterate separately. Across six predictive benchmarks, performance depends on the declared pipeline: replacing the tracker with the exact empirical target leaves the two regression deficits largely unchanged. Direct classification-rank models capture nearly all terminal objective energy on average, but a saved intermediate state exhibits substantial geometric deviation; a controlled sample-size study further separates empirical accuracy from population recovery. In distinct numerical-service workloads, exact on-request computation is faster in the tested classification settings, whereas Adam saves time relative to the tested full thin-SVD service for some dense wider-regression requests, alongside persistent geometric error. These diagnostics limit explanations based solely on terminal optimization accuracy and distinguish numerical cost from quality, rank coverage and freshness; they establish neither practical-tracker convergence nor predictive or deployment benefits from basis availability.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-18 in cs.LG).
Categorie arXiv: Machine Learning (stat.ML) ; Machine Learning (cs.LG); Computation (stat.CO).
Pagina del lavoro: https://arxiv.org/abs/2609.20454 — 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 2026-10-10T03:48:18.453Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).