math.STNov 2, 2026

Nonparametric Intensity Estimation for Covariate-Driven Poisson Processes Using Deep Learning

Authors: Atsutomo Yara, Yoshikazu Terada

Organizations: Graduate School of Engineering Science, the University of Osaka · RIKEN Center for Advanced Intelligence Project (AIP)

Abstract

We consider nonparametric maximum likelihood estimation of the intensity function of a Poisson process, allowing the intensity to depend on observed covariates. Such models describe how event rates vary with external conditions, including conditions under which the intensity becomes arbitrarily small or vanishes. However, risk analysis based on the Kullback-Leibler (KL) divergence typically requires the true intensity to be bounded away from zero, a restrictive assumption in applications. We develop a unified approach that avoids this assumption and derive an oracle inequality for the covariate-averaged Hellinger distance between the true intensity and the nonparametric maximum likelihood estimator (NPMLE). As an application of the oracle inequality, we establish convergence rates for NPMLEs based on deep neural networks (DNNs). Our results show that, as in nonparametric regression, the ability of DNNs to capture underlying structure leads to improved convergence rates. Specifically, DNN-based NPMLEs mitigate the curse of dimensionality when the true intensity has a compositional structure and automatically adapt to a low-dimensional Riemannian manifold structure of the event space. For intensity functions with a compositional structure, DNN-based NPMLEs achieve nearly minimax-optimal convergence rates without explicitly incorporating this structure into the network architecture. Simulations demonstrate that DNN-based estimators outperform kernel estimators in most settings, while manifold kernels remain competitive in some designs. Finally, we analyze stimulus-evoked neural spiking using data from the Allen Brain Observatory Visual Coding Neuropixels project. DNN-based NPMLEs provide better out-of-sample performance than a conditional kernel estimator, as evaluated by held-out log-likelihood.

Figures & tables

Appendix figures & tables15 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Neural Diffusion Intensity Models for Point Process Data

    Feb 27, 2026Xinlong Du, Harsha Honnappa, Vinayak RaoTemporal Point ProcessesVariational Inference

  2. Beyond Consistency: Inference for the Relative risk functional in Deep Nonparametric Cox Models

    Mar 25, 2026Sattwik Ghosal, Xuran Meng, Yi LiSurvival AnalysisSemiparametric Inference

  3. Flexible Intensities Matter: A Comprehensive Re-evaluation of Hawkes Processes and Neural Temporal Point Processes

    Nov 4, 2026Hendrik Mehrtens, Florian Buettner, Oliver StegleTemporal Point ProcessesHawkes Processes