Metraipolis › archive › dc_ccfd513e5789

When Has a Bayesian Neural Network Sampled Enough? Adaptive Inference Time with Statistical Guarantees — arXiv:2610.12212

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.12212
License (as archived)
CC0-1.0
Archived
2026-10-09T05:50:38.166Z
SHA-256 of the archived text
4aaf1b6bb5c7d8bbb588cf27d98375b833e4ef165c4532987ce84ca96665cdb1
Stable URL of this page
https://metraipolis.com/documento/dc_ccfd513e5789

How to cite

When Has a Bayesian Neural Network Sampled Enough? Adaptive Inference Time with Statistical Guarantees — arXiv:2610.12212 — arXiv (en), https://arxiv.org/abs/2610.12212 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ccfd513e5789 (Metraipolis archive dc_ccfd513e5789, sha256 4aaf1b6bb5c7d8bbb588cf27d98375b833e4ef165c4532987ce84ca96665cdb1)
BibTeX
@misc{dcccfd513e5789,
  title = {When Has a Bayesian Neural Network Sampled Enough? Adaptive Inference Time with Statistical Guarantees — arXiv:2610.12212},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.12212},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ccfd513e5789; sha256 4aaf1b6bb5c7d8bbb588cf27d98375b833e4ef165c4532987ce84ca96665cdb1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.12212. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Bayesian neural network predictions are commonly approximated using a fixed number of Monte Carlo samples per input, without controlling the resulting error that comes from this finite sample. We propose the use of confidence sequences to dynamically determine how many samples are needed while maintaining statistical guarantees. We consider several ways in which predictive probabilities are used, including identifying the most likely class, approximating the full predictive distribution, and resolving probability-threshold decisions. Sampling stops once the corresponding decision can be made with the desired guarantee. Experiments show that the method allocates the computational budget efficiently, assigning more samples to ambiguous inputs than to easy inputs while preserving reliable decisions and reducing overall latency relative to a fixed Monte Carlo budget.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.12212 — 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 2026-10-09T05:47:01.092Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).