Mixed LICORS: A Nonparametric Algorithm for Predictive State Reconstruction

Georg Goerg, Cosma Shalizi
Proceedings of the Sixteenth International Conference on Artificial Intelligence and Statistics, PMLR 31:289-297, 2013.

Abstract

We introduce mixed LICORS, an algorithm for learning nonlinear, high-dimensional dynamics from spatio-temporal data, suitable for both prediction and simulation. Mixed LICORS extends the recent LICORS algorithm (Goerg and Shalizi, 2012) from hard clustering of predictive distributions to a non-parametric, EM-like soft clustering. This retains the asymptotic predictive optimality of LICORS, but, as we show in simulations, greatly improves out-of-sample forecasts with limited data. The new method is implemented in the publicly-available R package LICORS.

Cite this Paper

BibTeX
@InProceedings{pmlr-v31-goerg13a, title = {Mixed LICORS: A Nonparametric Algorithm for Predictive State Reconstruction}, author = {Goerg, Georg and Shalizi, Cosma}, booktitle = {Proceedings of the Sixteenth International Conference on Artificial Intelligence and Statistics}, pages = {289--297}, year = {2013}, editor = {Carvalho, Carlos M. and Ravikumar, Pradeep}, volume = {31}, series = {Proceedings of Machine Learning Research}, address = {Scottsdale, Arizona, USA}, month = {29 Apr--01 May}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v31/goerg13a.pdf}, url = {https://proceedings.mlr.press/v31/goerg13a.html}, abstract = {We introduce mixed LICORS, an algorithm for learning nonlinear, high-dimensional dynamics from spatio-temporal data, suitable for both prediction and simulation. Mixed LICORS extends the recent LICORS algorithm (Goerg and Shalizi, 2012) from hard clustering of predictive distributions to a non-parametric, EM-like soft clustering. This retains the asymptotic predictive optimality of LICORS, but, as we show in simulations, greatly improves out-of-sample forecasts with limited data. The new method is implemented in the publicly-available R package LICORS.} }
Endnote
%0 Conference Paper %T Mixed LICORS: A Nonparametric Algorithm for Predictive State Reconstruction %A Georg Goerg %A Cosma Shalizi %B Proceedings of the Sixteenth International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2013 %E Carlos M. Carvalho %E Pradeep Ravikumar %F pmlr-v31-goerg13a %I PMLR %P 289--297 %U https://proceedings.mlr.press/v31/goerg13a.html %V 31 %X We introduce mixed LICORS, an algorithm for learning nonlinear, high-dimensional dynamics from spatio-temporal data, suitable for both prediction and simulation. Mixed LICORS extends the recent LICORS algorithm (Goerg and Shalizi, 2012) from hard clustering of predictive distributions to a non-parametric, EM-like soft clustering. This retains the asymptotic predictive optimality of LICORS, but, as we show in simulations, greatly improves out-of-sample forecasts with limited data. The new method is implemented in the publicly-available R package LICORS.
RIS
TY - CPAPER TI - Mixed LICORS: A Nonparametric Algorithm for Predictive State Reconstruction AU - Georg Goerg AU - Cosma Shalizi BT - Proceedings of the Sixteenth International Conference on Artificial Intelligence and Statistics DA - 2013/04/29 ED - Carlos M. Carvalho ED - Pradeep Ravikumar ID - pmlr-v31-goerg13a PB - PMLR DP - Proceedings of Machine Learning Research VL - 31 SP - 289 EP - 297 L1 - http://proceedings.mlr.press/v31/goerg13a.pdf UR - https://proceedings.mlr.press/v31/goerg13a.html AB - We introduce mixed LICORS, an algorithm for learning nonlinear, high-dimensional dynamics from spatio-temporal data, suitable for both prediction and simulation. Mixed LICORS extends the recent LICORS algorithm (Goerg and Shalizi, 2012) from hard clustering of predictive distributions to a non-parametric, EM-like soft clustering. This retains the asymptotic predictive optimality of LICORS, but, as we show in simulations, greatly improves out-of-sample forecasts with limited data. The new method is implemented in the publicly-available R package LICORS. ER -
APA
Goerg, G. & Shalizi, C.. (2013). Mixed LICORS: A Nonparametric Algorithm for Predictive State Reconstruction. Proceedings of the Sixteenth International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 31:289-297 Available from https://proceedings.mlr.press/v31/goerg13a.html.

Related Material