Efficient entropy-based detection of change-points in streaming data

Add to your list(s) Download to your calendar using vCal

• James Cruise (Heriot-Watt University)
• Monday 06 June 2011, 14:30-15:30
• MR12, Centre for Mathematical Sciences, Wilberforce Road, Cambridge.

If you have a question about this talk, please contact Elena Yudovina.

It is well-known that the entropy of an unknown stationary source can be consistently estimated using an estimator based on the lengths of long repeated sections of text. I will discuss a method for detecting change points in data sources based on similar information theory-based quantities. I will present the results of some simulations and theoretical results based on properties of the typical set which justify how successful this method can be.

Joint work with Oliver Johnson, Dino Sejdinovic, Christophe Andrieu, Ayalvadi Ganesh and Robert Piechocki

This talk is part of the Optimization and Incentives Seminar series.

This talk is included in these lists:

• All CMS events
• All Talks (aka the CURE list)
• CMS Events
• Cambridge talks
• DPMMS Lists
• DPMMS info aggregator
• DPMMS lists
• Economics and Computer Science Talks
• Hanchen DaDaDash
• Interested Talks
• MR12, Centre for Mathematical Sciences, Wilberforce Road, Cambridge
• Optimization and Incentives Seminar
• School of Physical Sciences
• Statistical Laboratory info aggregator
• Trust & Technology Initiative - interesting events
• bld31

Note that ex-directory lists are not shown.