BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Structural Markov laws / Geometry and HMC - Dr Simon Byrne
DTSTART:20150609T100000Z
DTEND:20150609T110000Z
UID:TALK59712@talks.cam.ac.uk
CONTACT:12852
DESCRIPTION:This talk will focus on two particular aspects of my research:
 \n\nSuppose that we wish to infer the structure of a graphical model: how 
 should we choose a prior over the space of possible graphs? I'll introduce
  the notion of a structural Markov property\, which requires that the stru
 cture of distinct components of the graph be conditionally independent giv
 en the existence of a separating component. This characterises an exponent
 ial family that is conjugate under sampling from compatible Markov distrib
 utions.\n\nIn the second part\, I will talk about various geometric aspect
 s of the Hamiltonian/Hybrid Monte Carlo (HMC) algorithm. I will explain ho
 w HMC can be extended to manifolds\, such as spheres and Stiefel manifolds
 \n(the manifold of orthogonal matrices). I will also describe how this geo
 metric understanding can guide the optimal tuning of the algorithm.\n
LOCATION:Engineering Department\, CBL Room BE-438
END:VEVENT
END:VCALENDAR