Metraipolis › archive › dc_23bfd8d77cdc

Estimating Implicit Expected Log Density Ratios — arXiv:2610.38151

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.38151
License (as archived)
CC0-1.0
Archived
2026-10-31T06:11:23.523Z
SHA-256 of the archived text
c931509366bfbbca5cf460440e02afcacf6aabe62426e7752270fd2ca3f54490
Stable URL of this page
https://metraipolis.com/documento/dc_23bfd8d77cdc

How to cite

Estimating Implicit Expected Log Density Ratios — arXiv:2610.38151 — arXiv (en), https://arxiv.org/abs/2610.38151 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_23bfd8d77cdc (Metraipolis archive dc_23bfd8d77cdc, sha256 c931509366bfbbca5cf460440e02afcacf6aabe62426e7752270fd2ca3f54490)
BibTeX
@misc{dc23bfd8d77cdc,
  title = {Estimating Implicit Expected Log Density Ratios — arXiv:2610.38151},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.38151},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_23bfd8d77cdc; sha256 c931509366bfbbca5cf460440e02afcacf6aabe62426e7752270fd2ca3f54490},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.38151. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

When exact probabilities cannot be computed, \emph{density ratio estimation (DRE)} is a key subroutine in the wide range of applications where density ratios appear, from experimental design to generative modelling and reinforcement learning. In this paper, we introduce the concept of an \emph{expected log density ratio (ELDR)}: log density ratios that are integrated under some third, possibly distinct measure. We show many problems with implicit densities where DRE is naïvely used are actually ELDR estimation tasks, and prove fundamental limitations on finite-sample ELDR estimation. Based on these results, we argue that the typical DRE-based approaches are unsuitable for ELDR estimation, and provide some foundational motivation towards bespoke ELDR estimators. To demonstrate, we propose a simple modification to some DRE methods that allows samples convergent to the integral distribution to appear in training data. We show through benchmarks that this can improve ELDR estimation error.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2610.38151 — 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 2026-10-31T06:07:08.632Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).