Metraipolis › archive › dc_24b91e32889e
Minimax bounds for watermarked and masked recursive discrete distribution estimation — arXiv:2608.31091
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.31091
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T08:40:04.978Z
- SHA-256 of the archived text
634b9257ce287354e7b653e10da5cdba002adebe2c53d1128c6d5c4124a30a56- Stable URL of this page
https://metraipolis.com/documento/dc_24b91e32889e
How to cite
Minimax bounds for watermarked and masked recursive discrete distribution estimation — arXiv:2608.31091 — arXiv (en), https://arxiv.org/abs/2608.31091 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_24b91e32889e (Metraipolis archive dc_24b91e32889e, sha256 634b9257ce287354e7b653e10da5cdba002adebe2c53d1128c6d5c4124a30a56)
BibTeX
@misc{dc24b91e32889e,
title = {Minimax bounds for watermarked and masked recursive discrete distribution estimation — arXiv:2608.31091},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.31091},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_24b91e32889e; sha256 634b9257ce287354e7b653e10da5cdba002adebe2c53d1128c6d5c4124a30a56},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.31091. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Watermarking has been proposed as a way to identify synthetic samples in estimation settings where no metadata is available to distinguish them from real samples, but its precise effects remain unexplored. In the absence of a distinguishing mechanism, it has been shown that adding synthetic samples significantly reduces the marginal efficacy of new real samples. In this work, we study the minimax loss of such recursive discrete distribution estimation in the presence of watermarks in contrast to the unassisted and oracle-assisted losses. When the fraction of real samples vanishes asymptotically, we provide a lower bound that shows that it is impossible to improve performance by adding watermarks unless the false negative rate of detection also vanishes. Additionally, we show that in most regimes, the worst-case losses of a sequence of simple deterministic estimators match the corresponding lower bounds up to constants. Finally, we propose masking, a randomization procedure that narrows the gap in the remaining regimes to a Jensen gap. We conjecture that a tighter lower bound argument can close this gap. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-01 in cs.LG). Categorie arXiv: Information Theory (cs.IT) ; Machine Learning (cs.LG); Statistics Theory (math.ST). Pagina del lavoro: https://arxiv.org/abs/2608.31091 — 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 2026-10-17T08:13:26.956Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).