• Corpus ID: 245906423

Bayesian Estimation of Multivariate Hawkes Processes with Inhibition and Sparsity

  title={Bayesian Estimation of Multivariate Hawkes Processes with Inhibition and Sparsity},
  author={Isabella Deutsch and Gordon J. Ross},
Hawkes processes are point processes that model data where events occur in clusters through the self-exciting property of the intensity function. We consider a multivariate setting where multiple dimensions can influence each other with intensity function to allow for excitation and inhibition, both within and across dimensions. We discuss how such a model can be implemented and highlight challenges in the estimation procedure induced by a potentially negative intensity function. Furthermore… 

Figures and Tables from this paper

Inference of multivariate exponential Hawkes processes with inhibition and application to neuronal activity

This paper proposes a maximum likelihood approach to estimate the interaction functions of a multivariate Hawkes process that can account for both exciting and inhibiting effects and shows that the proposed estimator performs better on synthetic data than alternative approaches.

Bayesian inference for aggregated Hawkes processes

A Bayesian estimation procedure for the parameters of a Hawkes process based on aggregated data is developed for temporal, spatio-temporal, and mutually exciting Hawkes processes where data are available over discrete time periods and regions.

A flexible, random histogram kernel for discrete-time Hawkes processes (preprint)

This work presents a flexible approach for modelling a variant of these, namely discrete-time Hawkes processes, using trans-dimensional Markov chain Monte Carlo inference techniques and can take the form of any step function, affording significantly more flexibility than a parametric form.

Scalable Variational Bayes methods for Hawkes processes

Multivariate Hawkes processes are temporal point processes extensively applied to model event data with dependence on past occurrences and interaction phenomena, e.g., neuronal spike trains, online



Bayesian estimation of nonlinear Hawkes process

This work proves that the posterior distribution is consistent on the graph adjacency matrix of the process, as well as a Bayesian estimator based on an adequate loss function and provides consistency guarantees on Bayesian methods for estimating this quantity.

Nonparametric Markovian Learning of Triggering Kernels for Mutually Exciting and Mutually Inhibiting Multivariate Hawkes Processes

A novel algorithm called MEMIP (Markovian Estimation of Mutually Interacting Processes) is proposed that makes use of polynomial approximation theory and self-concordant analysis in order to learn both triggering kernels and base intensities of events.

Graphical Modeling for Multivariate Hawkes Processes with Nonparametric Link Functions

It is shown that the Granger causality structure of such processes is fully encoded in the corresponding link functions of the model and a new nonparametric estimator of the link functions based on a time‐discretized version of the point process is introduced.

Mutually Regressive Point Processes

This paper introduces the first general class of Bayesian point process models extended with a nonlinear component that allows both excitatory and inhibitory relationships in continuous time and derives a fully Bayesian inference algorithm for these processes using Polya-Gamma augmentation and Poisson thinning.

Hawkes Process Inference With Missing Data

This paper develops a method to sample over the posterior distribution of unobserved events in a multivariate Hawkes process and demonstrates the efficacy of the approach, and its utility in improving predictive power and identifying latent structure in real-world data.

Bayesian Inference for Hawkes Processes

This paper explores and compares two approaches to Bayesian inference based on an underlying clustering and branching structure in the Hawkes process and compares them numerically.

The Neural Hawkes Process: A Neurally Self-Modulating Multivariate Point Process

This generative model allows past events to influence the future in complex and realistic ways, by conditioning future event intensities on the hidden state of a recurrent neural network that has consumed the stream of past events.

Modelling sparsity, heterogeneity, reciprocity and community structure in temporal interaction data

A family of models based on self-exciting Hawkes point processes in which events depend on the history of the process are proposed, which captures the fact that interactions may arise as a response to past interactions, or due to shared interests between individuals.

Handling missing data in self-exciting point process models

Estimation of slowly decreasing Hawkes kernels: application to high-frequency order book dynamics

We present a modified version of the non parametric Hawkes kernel estimation procedure studied in Bacry and Muzy [arXiv:1401.0903, 2014] that is adapted to slowly decreasing kernels. We show on