English

The extremal point process of branching Brownian motion in $\mathbb{R}^d$

Probability 2023-12-01 v2

Abstract

We consider a branching Brownian motion in Rd\mathbb{R}^d with d1d \geq 1 in which the position Xt(u)RdX_t^{(u)}\in \mathbb{R}^d of a particle uu at time tt can be encoded by its direction θt(u)Sd1\theta^{(u)}_t \in \mathbb{S}^{d-1} and its distance Rt(u)R^{(u)}_t to 0. We prove that the {\it extremal point process} δθt(u),Rt(u)mt(d)\sum \delta_{\theta^{(u)}_t, R^{(u)}_t - m_t^{(d)}} (where the sum is over all particles alive at time tt and mt(d)m^{(d)}_t is an explicit centring term) converges in distribution to a randomly shifted decorated Poisson point process on Sd1×R\mathbb{S}^{d-1} \times \mathbb{R}. More precisely, the so-called {\it clan-leaders} form a Cox process with intensity proportional to D(θ)e2r dr dθD_\infty(\theta) e^{-\sqrt{2}r} ~\mathrm{d} r ~\mathrm{d} \theta , where D(θ)D_\infty(\theta) is the limit of the derivative martingale in direction θ\theta and the decorations are i.i.d. copies of the decoration process of the standard one-dimensional branching Brownian motion. This proves a conjecture of Stasi\'nski, Berestycki and Mallein (Ann. Inst. H. Poincar\'{e} 57:1786--1810, 2021), and builds on that paper and on Kim, Lubetzky and Zeitouni (arXiv:2104.07698).

Keywords

Cite

@article{arxiv.2112.08407,
  title  = {The extremal point process of branching Brownian motion in $\mathbb{R}^d$},
  author = {Julien Berestycki and Yujin H. Kim and Eyal Lubetzky and Bastien Mallein and Ofer Zeitouni},
  journal= {arXiv preprint arXiv:2112.08407},
  year   = {2023}
}

Comments

20 pages, 4 figures; Version 2 includes referees comments