Metraipolis › archive › dc_c99ce4b09f86

The Statistical Geometry of Latent Recovery in Hidden Markov Models — arXiv:2611.00680

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.00680
License (as archived)
CC0-1.0
Archived
2026-11-03T11:28:57.813Z
SHA-256 of the archived text
b30481db2408a038baa774e33db6c1d4f4de098b95f011ea34a2d7e2b574dcff
Stable URL of this page
https://metraipolis.com/documento/dc_c99ce4b09f86

How to cite

The Statistical Geometry of Latent Recovery in Hidden Markov Models — arXiv:2611.00680 — arXiv (en), https://arxiv.org/abs/2611.00680 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c99ce4b09f86 (Metraipolis archive dc_c99ce4b09f86, sha256 b30481db2408a038baa774e33db6c1d4f4de098b95f011ea34a2d7e2b574dcff)
BibTeX
@misc{dcc99ce4b09f86,
  title = {The Statistical Geometry of Latent Recovery in Hidden Markov Models — arXiv:2611.00680},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.00680},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c99ce4b09f86; sha256 b30481db2408a038baa774e33db6c1d4f4de098b95f011ea34a2d7e2b574dcff},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00680. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Hidden Markov models (HMMs) offer an important capability to interpret fitted latent states and transitions. When emission distributions nearly coincide, a small observation-density error does not ensure accurate estimation of the latent quantities needed for interpretation. This motivates us to characterize convergence rates for latent recovery that account for emission separation. Our main contribution lies in deriving deterministic inverse inequalities that convert Hellinger error between fitted and true densities into bounds on latent recovery errors. We develop these bounds for multivariate Gaussian HMMs with a common, known emission covariance matrix and combine them with a Hellinger estimation guarantee for the global maximum likelihood estimator to obtain latent recovery rates. Although the joint observation distribution is a Gaussian mixture with exponentially many path components, they share the same emission centers across time. Leveraging this shared structure, we show that the separation exponents are governed by the maximum number of simultaneously approaching centers rather than the number of path components. Under exact specification, the global bounds on state-sequence probability discrepancies and the 1-Wasserstein loss for latent location distributions exhibit sharp separation exponents that do not increase with the number of selected times. Moreover, sufficiently small observation-density error guarantees unique matching between fitted and true emission centers, which yields error bounds for individual emission centers and transition rows. Under over-specification, individual split-state transition rows are not necessarily identifiable, so we quantify aggregate latent recovery errors and show that state-sequence probability bounds incur larger separation exponents compared to exact specification. We conduct synthetic experiments to validate our theoretical results.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv stat.ML, nuovi lavori del giorno).
Categorie arXiv: Statistics Theory (math.ST) ; Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2611.00680 — 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 2026-11-03T11:03:22.233Z dalla pagina https://arxiv.org/list/stat.ML/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).