Martingale Posterior Cox Processes

Abstract

Cox processes provide a principled Bayesian nonparametric framework for modeling event-based data through an underlying intensity function. However, existing inference methods for estimating the intensity typically rely on computationally expensive Markov chain Monte Carlo sampling or approximate inference techniques. In addition, to ensure tractability, these methods often define priors over indirect latent structures, making them challenging to interpret. In this paper, we introduce the Martingale Posterior Cox Process (MPCP), which recasts Bayesian intensity estimation as inference over unobserved events given the observed event history. This perspective avoids the need to define complex priors while retaining the flexibility of nonparametric modeling. We propose a scalable, GPU-friendly copula-based predictive update, and provide strong theoretical guarantees for the convergence of the predictive resampling algorithm. Empirically, we show that MPCP provides excellent performance in both simulations and real data at a fraction of the computational cost of competing Bayesian approaches.

Federated Martingale Posterior Samping
Boning Zhang, Matteo Zecchin, Mingzhao Guo +2
arXiv25 Sep 2026PreprintarXiv licenceFull textStatisticsarXiv
Post-Corrected Raw-Score Martingale Posterior Sampling for von Mises-Fisher Models
Yi Xu, Xinye Chen, Sheng Jiang
arXiv4 Sep 2026PreprintarXiv licenceFull textStatisticsarXiv
Aggregation of value processes for semi-martingale BSDEs with jumps
Dylan Possamaï, Marco Rodrigues, Alexandros Saplaouras
arXiv20 Sep 2026PreprintarXiv licenceFull textOptimisation & control ProbabilityarXiv
Young Parabolic PDEs and the Martingale Problem for Young SDEs
Fabio Bugini, Michele Coghi, Khoa Lê +1
arXiv19 Oct 2026PreprintCC0Full textAnalysis & PDEs ProbabilityarXiv
Martingale and analytic dimensions
Sylvester Eriksson-Bique, Mathav Murugan
arXiv29 Sep 2026PreprintarXiv licenceFull textGeometry & topology ProbabilityarXiv

Cite

BibTeX RIS

BibTeX

@misc{rooijakkers2026martingale,
  title = {{Martingale Posterior Cox Processes}},
  author = {Joshua Rooijakkers and Edwin Fong},
  howpublished = {arXiv},
  year = {2026},
  month = oct,
  doi = {10.48550/arxiv.2610.24787},
  eprint = {2610.24787},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.24787},
}

RIS

TY  - UNPB
TI  - Martingale Posterior Cox Processes
AU  - Joshua Rooijakkers
AU  - Edwin Fong
PY  - 2026
DA  - 2026/10/17
PB  - arXiv
DO  - 10.48550/arxiv.2610.24787
UR  - https://arxiv.org/abs/2610.24787
AB  - Cox processes provide a principled Bayesian nonparametric framework for modeling event-based data through an underlying intensity function. However, existing inference methods for estimating the intensity typically rely on computationally expensive Markov chain Monte Carlo sampling or approximate inference techniques. In addition, to ensure tractability, these methods often define priors over indirect latent structures, making them challenging to interpret. In this paper, we introduce the Martingale Posterior Cox Process (MPCP), which recasts Bayesian intensity estimation as inference over unobserved events given the observed event history. This perspective avoids the need to define complex priors while retaining the flexibility of nonparametric modeling. We propose a scalable, GPU-friendly copula-based predictive update, and provide strong theoretical guarantees for the convergence of the predictive resampling algorithm. Empirically, we show that MPCP provides excellent performance in both simulations and real data at a fraction of the computational cost of competing Bayesian approaches.
ER  -

Abstract

Related

Cite