Metraipolis › archive › dc_6d44816229ff

Deterministic Bounds on Accuracy and Stability of Metric-Space Regression and Classification — arXiv:2610.22564

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.22564
License (as archived)
CC0-1.0
Archived
2026-10-19T08:48:20.883Z
SHA-256 of the archived text
2137d445a7907e0912d800897b12be1243ebbf3e769dcf4cda324656d21b66a1
Stable URL of this page
https://metraipolis.com/documento/dc_6d44816229ff

How to cite

Deterministic Bounds on Accuracy and Stability of Metric-Space Regression and Classification — arXiv:2610.22564 — arXiv (en), https://arxiv.org/abs/2610.22564 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6d44816229ff (Metraipolis archive dc_6d44816229ff, sha256 2137d445a7907e0912d800897b12be1243ebbf3e769dcf4cda324656d21b66a1)
BibTeX
@misc{dc6d44816229ff,
  title = {Deterministic Bounds on Accuracy and Stability of Metric-Space Regression and Classification — arXiv:2610.22564},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.22564},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6d44816229ff; sha256 2137d445a7907e0912d800897b12be1243ebbf3e769dcf4cda324656d21b66a1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.22564. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Data-driven approaches often face ambiguity in datasets due to sensor or target noise, insufficient information, and noise in the input data. While best-fit machine learning methods can accommodate such noise through uncertainty estimates, they are prone to overfitting and it is challenging to quantify ambiguity of the relation between inputs and targets. We introduce a geometric framework that quantifies this ambiguity through the average kernel size, computed with data-dependent, i.e. model-independent, feasible sets derived from worst-case input and target noise. The framework provides computable, deterministic, non-asymptotic bounds on the best achievable empirical error and accuracy for a finite, constructed dataset, independent of the predictive model class, and applies to regression and classification with pseudo-metric input spaces and metric target spaces. The ambiguity of the input-target relation implies three consequences: an empirical error floor, an accuracy-stability trade-off, and, under standard probabilistic assumptions, a strictly positive distribution-training error gap when training below the accuracy bounds. Under standard Borel assumptions for Euclidean norms, the distributional analogue of the average kernel size is related to Bayes risk as it reduces to the optimal distribution root-mean-squared error times the square root of two. Experiments spanning tabular regression, image regression and classification datasets yield nontrivial bounds on the best achievable empirical error and accuracy on a constructed dataset, alongside descriptive comparisons with model performance on the original datasets. The bounds provide a computable, model-independent reference scale on the constructed dataset and comparisons with model performance on the original dataset are descriptive.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Optimization and Control (math.OC).
Pagina del lavoro: https://arxiv.org/abs/2610.22564 — 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 2026-10-19T08:42:40.215Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).