BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Bayesian nonparametric estimation of the intensities in multivaria
 te Hawkes processes - Judith Rousseau (Oxford)
DTSTART:20180126T160000Z
DTEND:20180126T170000Z
UID:TALK98677@talks.cam.ac.uk
CONTACT:Quentin Berthet
DESCRIPTION:Joint wortk with Sophie Donnet and Vincent Rivoirard.\n\nHawke
 s processes are special cases of point processes. In some cases they are a
 lso called self excited Poisson processes. Generally speaking\, if (N_t\, 
 t ∈ [0\, T])is the point process\, Hawkes processes are caracterised by 
 having a conditional intensity function given by λ(t) = (ν +int_0^t−\
 nh(t − u)dN_u)_+. \n\nIn this work we are interested in estimating the p
 arameters (ν\, h) in the context of multivariate Hawkes processes\, using
  Bayesian nonparametric approaches. We propose generic conditions on the t
 rue parameters ν\, h and the associated prior distributions to obtain pos
 terior concentration rates under the L1 norm for these parameters. We appl
 y these conditions to various families of prior models and finally we pres
 ent a simulation study in the context of neuroscience.
LOCATION:MR12
END:VEVENT
END:VCALENDAR