Metraipolis › archive › dc_75a4ecef2962
Posterior Frequencies and the Cost of Not Fitting: A Correction to a Memorization Lower Bound — arXiv:2610.20402
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.20402
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T14:23:52.114Z
- SHA-256 of the archived text
f42779b80cf942ecc08117e98727cecd338e521623893da9472ee3a4359c013f- Stable URL of this page
https://metraipolis.com/documento/dc_75a4ecef2962
How to cite
Posterior Frequencies and the Cost of Not Fitting: A Correction to a Memorization Lower Bound — arXiv:2610.20402 — arXiv (en), https://arxiv.org/abs/2610.20402 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_75a4ecef2962 (Metraipolis archive dc_75a4ecef2962, sha256 f42779b80cf942ecc08117e98727cecd338e521623893da9472ee3a4359c013f)
BibTeX
@misc{dc75a4ecef2962,
title = {Posterior Frequencies and the Cost of Not Fitting: A Correction to a Memorization Lower Bound — arXiv:2610.20402},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.20402},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_75a4ecef2962; sha256 f42779b80cf942ecc08117e98727cecd338e521623893da9472ee3a4359c013f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.20402. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Feldman's memorization lower bound assigns a frequency coefficient based on how often a point appears in the training sample. We give an exact three-point counterexample to its conditional and averaged forms, using independent fair labels and a permutation-equivariant learner. A sequence of sampling priors makes the ratio of the proposed penalty to actual excess risk grow exponentially, ruling out a universal positive constant-factor repair. The priors vary with sample size, the offending profiles become rare, and both quantities vanish. Retaining the original model, we obtain an exact replacement using full-sample posterior probabilities. Under exchangeability, these depend on multiplicity and the complete frequency profile. We characterize the largest multiplicity-only coefficients valid for unrestricted learners. The original coefficient has the posterior-mean form of Good's exact frequency formula and is an occupancy-weighted average of the corrected coefficients. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (stat.ML) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.20402 — 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 2026-10-15T13:53:35.967Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).