On simulation of continuous determinantal point processes

TL;DR

This paper reviews and enhances simulation algorithms for continuous determinantal point processes, focusing on efficiency improvements and conditional simulation methods, with implementations available as open source.

Contribution

It introduces improved algorithms for simulating continuous DPPs, especially Fourier-based projection DPPs, and provides open source software for practical use.

Findings

Enhanced simulation speed for Fourier-based projection DPPs

Detailed methods for conditional simulation of DPPs

Open source implementation available

Abstract

We review how to simulate continuous determinantal point processes (DPPs) and improve the current simulation algorithms in several important special cases as well as detail how certain types of conditional simulation can be carried out. Importantly we show how to speed up the simulation of the widely used Fourier based projection DPPs, which arise as approximations of more general DPPs. The algorithms are implemented and published as open source software.