PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Cross-entropy optimization for independent process analysis
Zoltan Szabo, Barnabas Poczos and András Lorincz
In: 6th International Conference on Independent Component Analysis and Blind Source Separation (ICA), 5-8 Mar 2006, Charleston, SC, USA.

There is a more recent version of this eprint available. Click here to view it.

Abstract

We treat the problem of searching for hidden multi-dimensional independent auto-regressive processes. First, we transform the problem to Independent Subspace Analysis (ISA). Our main contribution concerns ISA. We show that under certain conditions, ISA is equivalent to a combinatorial optimization problem. For the solution of this optimization we apply the cross-entropy method. Numerical simulations indicate that the cross-entropy method can provide considerable improvements over other state-of-the-art methods.

PDF - PASCAL Members only - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Conference or Workshop Item (Paper)
Additional Information:http://dx.doi.org/10.1007/11679363_113
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Learning/Statistics & Optimisation
Theory & Algorithms
ID Code:8360
Deposited By:Zoltan Szabo
Deposited On:01 December 2011

Available Versions of this Item