Monte Carlo Inference for Alpha-Stable Processes

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

• Tatjana Lemke, Fraunhofer Institute and Signal Processing and COmmunications Laboratory, CUED
• Monday 06 February 2012, 14:00-15:00
• LR5, Engineering, Department of.

If you have a question about this talk, please contact Rachel Fogg.

In this talk we will present a novel approach to inference in previously intractable alpha-stable stochastic processes. The methods are based on a Poisson sum series representation of the alpha-stable noise process and a modified Poisson sum series representation of the alpha-stable Levy process. Both representations provide a conditionally Gaussian framework, and hence allow for the use of an auxiliary variables Monte Carlo simulation scheme. To overcome the issues due to truncation of the series, residual approximations are developed. Simulations will be given of parameter estimation including model parameters, model order and alpha-stable distribution parameters for discrete-time autoregressive processes driven by alpha-stable innovations.

This talk is part of the Signal Processing and Communications Lab Seminars series.

This talk is included in these lists:

• All Talks (aka the CURE list)
• Cambridge Centre for Data-Driven Discovery (C2D3)
• Cambridge University Engineering Department Talks
• Cambridge talks
• Centre for Smart Infrastructure & Construction
• Chris Davis' list
• Computational Continuum Mechanics Group Seminars
• Featured lists
• Information Engineering Division seminar list
• Interested Talks
• LR5, Engineering, Department of
• School of Technology
• Signal Processing and Communications Lab Seminars
• Trust & Technology Initiative - interesting events
• bld31
• ndk22's list
• ob366-ai4er
• rp587

Note that ex-directory lists are not shown.