Approximate Inference for Continuous Time Markov Processes

54 mins 35 secs, 322.51 MB, Flash Video 480x360, 25.0 fps, 44100 Hz, 806.72 kbits/sec

Share this media item:

Embed this media item:

<iframe width="_width_" height="_height_" src="https://sms.cam.ac.uk/media/1104/embed" frameborder="0" scrolling="no" allowfullscreen></iframe>

Choose size:

About this item

Available Formats

About this item

Description:	Opper, M (Technische Universität Berlin) Thursday 19 June 2008, 11:30-12:30 Inference and Estimation in Probabilistic Time-Series Models

Created:

2008-06-25 11:46

Collection:

Statistical Theory and Methods for Complex, High-Dimensional Data

Publisher:

Isaac Newton Institute

Opper, M

Language:

eng (English)

Credits:

Author:	Opper, M
Producer:	Steve Greenham


Abstract:	Continuous time Markov processes (such as jump processes and diffusions) play an important role in the modelling of dynamical systems in many scientific areas. In a variety of applications, the stochastic state of the system as a function of time is not directly observed. One has only access to a set of nolsy observations taken at a discrete set of times. The problem is then to infer the unknown state path as best as possible. In addition, model parameters (like diffusion constants or transition rates) may also be unknown and have to be estimated from the data. While it is fairly straightforward to present a theoretical solution to these estimation problems, a practical solution in terms of PDEs or by Monte Carlo sampling can be time consuming and one is looking for efficient approximations. I will discuss approximate solutions to this problem such as variational approximations to the probability measure over paths and weak noise expansions.

Abstract:

Continuous time Markov processes (such as jump processes and diffusions) play an important role in the modelling of dynamical systems in many scientific areas.

In a variety of applications, the stochastic state of the system as a function of time is not directly observed. One has only access to a set of nolsy observations taken at a discrete set of times. The problem is then to infer the unknown state path as best as possible. In addition, model parameters (like diffusion constants or transition rates) may also be unknown and have to be estimated from the data. While it is fairly straightforward to present a theoretical solution to these estimation problems, a practical solution in terms of PDEs or by Monte Carlo sampling can be time consuming and one is looking for efficient approximations. I will discuss approximate solutions to this problem such as variational approximations to the probability measure over paths and weak noise expansions.

Available Formats

Format	Quality	Bitrate	Size
MPEG-4 Video	480x360	1.84 Mbits/sec	753.53 MB	View	Download
WebM	480x360	595.97 kbits/sec	237.90 MB	View	Download
Flash Video *	480x360	806.72 kbits/sec	322.51 MB	View	Download
iPod Video	480x360	505.28 kbits/sec	202.00 MB	View	Download
QuickTime	384x288	848.66 kbits/sec	339.28 MB	View	Download
MP3	44100 Hz	125.02 kbits/sec	49.77 MB	Listen	Download
Auto	(Allows browser to choose a format it supports)