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.
- David Barber (UCL London, UK)
- Silvia Chiappa (MPI Tuebingen, Germany)
- Taylan Cemgil (University of Cambridge, UK)