HAL Id: hal-02437229
https://hal.archives-ouvertes.fr/hal-02437229
Submitted on 13 Jan 2020
HAL is a multi-disciplinary open access
archive for the deposit and dissemination of sci-entific research documents, whether they are pub-lished or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers.
L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de recherche français ou étrangers, des laboratoires publics ou privés.
Nonparametric estimation of the mark density of Exponential Shot-Noise
Paul Ilhe, Eric Moulines, François Roueff, Antoine Souloumiac
To cite this version:
Paul Ilhe, Eric Moulines, François Roueff, Antoine Souloumiac. Nonparametric estimation of the mark density of Exponential Shot-Noise. 10e Journées du groupe Modélisation Aléatoire et Statistique de la SMAI, Aug 2014, Toulouse, France. 2014. �hal-02437229�
Nonparametric estimation of the mark density
of Exponential Shot-Noise
P. Ilhe, E. Moulines, F. Roueff (ilhe,moulines,roueff@telecom-paristech.fr)
A. Souloumiac (antoine.souloumiac@cea.fr)
I
NTRODUCTION
Shot-noise processes - or Filtered Marked Point Processes - are natural models for phenomenons that can be represented as a linear filtration of sums of independent jumps (marks) (Yi)i∈Z
arrived at random times (Ti)i∈Z. There are particularly adapted to model data transfers in telecommunication or interacting particles in physics.Based on a low-frequency sample of the
Shot-Noise (X1, · · · , Xn), we introduce a novel nonparametric estimator of the mark density when arrival times follow a Poisson Process with intensity λ and the filter is of the form
h(t) = e−αt using a "plug-in" method with the empirical characteristic function ˆϕn(u) = n∆ −1 Pnk=1 eiuXk .
P
ROBLEM
We consider the stationary process (X
t)
t≥0defined by:
X
t=
X
Tk≤t
Y
ke
−α(t−Tk)(1)
where:
1.
P
kδ
Tk,Ykis a Poisson random measure on R
2with intensity measure λLeb ⊗ F
2. λ, α > 0
3. Y
0has a p.d.f. θ which belong to the class:
Θ
C,K,L,a,β= {θ : θ
p.d.f. ,
R
R
x
8
θ(x)dx ≤ K,
R
R
|u|
β
|ϕ
Y
(u)|du ≤ L, |ϕ
Y(u)| ≥ Ce
−au2
}
From its definition and under Assumptions 1-3, the characteristic function ϕ
X0of X
0is non
zero,differentiable and given by:
ϕ
X0(u) = exp λ
R
0∞(ϕ
Y(ue
−αs) − 1) ds
,
u ∈ R
S
YNTHETIC SCHEME
Figure 1:
Simulation of a Shot-Noise sample path
I
NVERSE PROBLEM AND ESTIMATOR
Inversion formula:
Differentiating the characteristic function ϕ
X0gives:
ϕ
Y(u) = 1 + u
αλ ϕ0X0(u)
ϕX0(u)
,
u ∈ R
Estimation issues
:
Tempted to construct a "plug-in" estimator using the empirical characteristic (ECF) function but:
• ˆ
ϕ
n(u)
might take arbitrary small values
• The "pluged-in" integrand might diverge
"Plug-in" estimator
We then propose a mark density estimator ˆ
θ
ngiven by:
ˆ
θ
n(x)
= 2 max
∆R
Z
h−1n 0e
−ixu1 + u
α
λ
ˆ
ϕ
0n(u)
ˆ
ϕ
n(u)
1
| ˆϕn(u)|≥κn!
, 0
!
(2)
where
h
n=
log(n)6a 1/2and κ
n=
C2e
−ah −2 n=
C 2n
−1/6Theoritical result :
sup
θ∈ΘC,K,L,a,βE
θˆ
θ
n− θ
2 ∞. log(n)
−βN
UMERICAL
R
ESULTS
Illustration of our algorithm with two
numeri-cal examples with λ = 4.10
5, α = 3, 5.10
5:
• Marks
follows
a
gaussian
mixture
P
3i=1
p
iN
µi,σi2(x)
with:
p = [0.3 0.5 0.2] , µ = [4 12 22] , σ = [1 1 0.5]
Figure 2:
Gaussian mixture case
• Marks
follows
a
gamma
mixture
P
3i=1
p
iG
a,βi(x)
with :
a = 2 , p = [0.2 0.3 0.5] , β = [3 6 12]
Figure 3:
Gamma mixture case
A
LGORITHM
Algorithm 1:
Nonparametric mark density estimator
Input: Shot-noise observations X1, · · · , Xn
1. Choose ∆ > 0.
2. Compute the histogram (Hi)i∈Z of observations with bins of size ∆ :
Hi = {Xk ∈ [∆i; ∆(i + 1)]}/n 3. Set (dHi)i∈Z by dHi = ∆iHi
4. Set N = 2∆ 16 and compute Xφ = FFT(H, N ), dXφ = FFT(dH, N ) It gives for k = 1, · · · , N , Xφk ' ˆϕn
− 2π(k−1)N ∆ and dXφk ' −i ˆϕ0n
− 2π(k−1)N ∆ 5. Compute the ECF estimator : ˆϕY n 2π(k−1)
N ∆ = 1 + 2πα(k−1) N ∆λ dXφk dXφk
6. Compute the density estimator by : ˆθn = N ∆2 F F T ( ˆϕY n, N )
R
EMARKS
• The rate of convergence depends on the smoothness of the mark distribution
• The distribution F
Xof X
0is regularly varying at 0 with index λ/α
,→
One can use Hill’s estimator to estimate λ/α
• When the mark distribution is a mixture of exponential laws, a parametric approach is possible
R
EFERENCES
[1] Lowen, Steven B and Teich, Malvin C, Power-law shot noise, Information Theory, IEEE Transactions on, 36(6) (1990) 1302–1318.
[2] Iksanov A. and Jurek Z., Shot noise distributions and selfdecomposability, Taylor & Francis, (2003).
[3] Neumann M. and Reiß M., Nonparametric estimation for Lévy processes from low-frequency observations, Bernoulli, 15(1) (2009) 223–248.
[4] Gugushvili S., Nonparametric estimation of the char-acteristic triplet of a discretely observed Lévy process, Journal of Nonparametric Statistics, (2009).