Inference and estimation in probabilistic time-series models

Workshop theme

Time-series analysis throws up interesting problems which remain fundamental to several key and as yet unsolved application areas. For example, Bayesian time-series models typically couple all time-points of the series, resulting in intractable inference in high-dimensional latent spaces and therefore requiring approximation.

The workshop will discuss both theories and applications related to probabilistic approaches to time-series analysis. Viewpoints and experiences from researchers belonging to different communities, including machine learning, statistics and statistical physics, are particularly encouraged. For example, approximate inference in the machine learning community tends to be more focussed on deterministic/variational approaches, whilst the statistics community tends to prefer sampling approaches. Amongst others, discussions related to this topic would be appreciated.

More generally, advances in practical and theoretical issues related to probabilistic approaches to time-series modelling, including for example inference, estimation, prediction, classification, clustering and source separation, are appreciated. Novel application areas and the challenges that they bring are also welcome.

Applications for this workshop are now closed

The Organisers would like to thank the following sponsors for their generous support of the event:

Timetable

Wednesday 18th June 2008
13:00 to 14:00	Registration	Room 1
14:00 to 15:00	Simon Godsill University of Cambridge Sequential inference for dynamically evolving groups of objects	Room 1
15:00 to 15:30	Tea	No Room Required
15:30 to 16:10	Yuzhi Cai University of Plymouth A Bayesian method for non-Gaussian autoregressive quantile function time series models	Room 1
16:10 to 16:50	Xiaodong Luo University of Oxford State estimation in high dimensional systems: the method of the ensemble unscented Kalman filter	Room 1
16:50 to 17:30	A modern perspective on auxiliary particle filters	Room 1
17:30 to 18:30	Poster Session	Discussion Room

Thursday 19th June 2008
09:00 to 09:40	Valderio Reisen Universidade Federal do Espirito Santo Estimating multiple fractional seasonal long-memory parameter	Room 1
09:40 to 10:20	Yuan Shen Aston University Variational Markov Chain Monte Carlo for inference in partially observed stochastic dynamic systems	Room 1
10:20 to 11:00	Richard Turner University College London Two problems with variational expectation maximisation for time-series models	Room 1
11:00 to 11:30	Coffee	No Room Required
11:30 to 12:30	Manfred Opper Technische Universität Berlin Approximate Inference for Continuous Time Markov Processes	Room 1
12:30 to 13:30	Lunch at Wolfson Court/Churchill College	No Room Required
14:00 to 15:00	Recent applications of spatial point processes to multiple-object tracking	Room 1
15:00 to 15:20	Tea	No Room Required
15:20 to 16:00	Risi Kondor University College London Multi-object tracking with representations of the symmetric group	Room 1
16:00 to 17:00	Chris Williams University of Edinburgh Factorial switching linear dynamical systems for physiological condition monitoring	Room 1
17:00 to 17:30	Stephen Roberts University of Oxford Bayesian Gaussian process models for multi-sensor time-series prediction	Room 1
17:30 to 18:30	Wine reception/poster session	Discussion Room

Friday 20th June 2008
09:00 to 09:40	Geoffrey McLachlan University of Queensland Clustering of time course gene-expression data via mixture regression models	Room 1
09:40 to 10:20	Michalis Titsias University of Manchester Markov chain Monte Carlo algorithms for Gaussian processes	Room 1
10:20 to 11:00	John Aston University of Warwick Is that really the pattern we're looking for? Bridging the gap between statistical uncertainty and dynamic programming algorithms	Room 1
11:00 to 11:30	Coffee	No Room Required
11:30 to 12:30	Adaptive Monte Carlo Markov Chains	Room 1
12:30 to 13:30	Lunch at Wolfson Court/Churchill College	No Room Required
14:00 to 15:00	Omiros Papaspiliopoulos Universitat Pompeu Fabra A methodological framework for Monte Carlo estimation of continuous-time processes	Room 1
15:00 to 15:30	Tea	No Room Required
15:30 to 16:10	High frequency variability and microstructure bias	Room 1
16:10 to 17:10	Zoubin Ghahramani University of Cambridge Nonparametric Bayesian times series models: infinite HMMs and beyond	Room 1

Inference and estimation in probabilistic time-series models

Speakers

John Aston University of Warwick
Yuzhi Cai University of Plymouth
Zoubin Ghahramani University of Cambridge
Simon Godsill University of Cambridge
Risi Kondor University College London
Xiaodong Luo University of Oxford
Geoffrey McLachlan University of Queensland
Manfred Opper Technische Universität Berlin
Omiros Papaspiliopoulos Universitat Pompeu Fabra
Valderio Reisen Universidade Federal do Espirito Santo
Stephen Roberts University of Oxford
Yuan Shen Aston University
Michalis Titsias University of Manchester
Richard Turner University College London
Chris Williams University of Edinburgh

Show All

Inference and estimation in probabilistic time-series models

Workshop theme

Additional Sponsor

Applications for this workshop are now closed

Timetable

Speakers

Supported By

Register for updates