BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Analysis of Networks via the Sparse β-Model - Chenlei Leng\, Univ
 ersity of Warwick
DTSTART:20190301T160000Z
DTEND:20190301T170000Z
UID:TALK115924@talks.cam.ac.uk
CONTACT:Dr Sergio Bacallado
DESCRIPTION: We propose the Sparse β-Model\, a new network model that int
 erpolates the celebrated Erdos-Renyi model and the more recent β-model th
 at assigns one different parameter to each node. By a novel reparametrizat
 ion of the β-model to distinguish global and local sparseness and assumin
 g that many parameters therein are zero\, our model can drastically reduce
  the dimensionality of the β-model. For estimating its parameters\, we fo
 rmulate a penalized likelihood approach with the l_0 penalty. Remarkably\,
  we show via a monotonicity lemma that the seemingly combinatorial computa
 tional problem due to the l_0 penalty can be overcome by assigning nonzero
  parameters to those nodes with the largest degrees. We show further that 
 a β-min condition guarantees our method to identify the true model and pr
 ovide excess risk bounds for the estimated parameters. The estimation proc
 edure enjoys good finite sample properties as shown by simulation study. T
 he usefulness of our model is further illustrated via the analysis of a mi
 crofinance take up example.\n
LOCATION:MR12
END:VEVENT
END:VCALENDAR