Computer Science – Information Theory
Scientific paper
2007-01-08
IEEE Transactions on Information Theory, vol. 55, pp. 1423-1429, March 2009
Computer Science
Information Theory
12 pages, to appear in IEEE Transactions on Information Theory
Scientific paper
The classical alternating minimization (or projection) algorithm has been successful in the context of solving optimization problems over two variables. The iterative nature and simplicity of the algorithm has led to its application to many areas such as signal processing, information theory, control, and finance. A general set of sufficient conditions for the convergence and correctness of the algorithm is quite well-known when the underlying problem parameters are fixed. In many practical situations, however, the underlying problem parameters are changing over time, and the use of an adaptive algorithm is more appropriate. In this paper, we study such an adaptive version of the alternating minimization algorithm. As a main result of this paper, we provide a general set of sufficient conditions for the convergence and correctness of the adaptive algorithm. Perhaps surprisingly, these conditions seem to be the minimal ones one would expect in such an adaptive setting. We present applications of our results to adaptive decomposition of mixtures, adaptive log-optimal portfolio selection, and adaptive filter design.
Niesen Urs
Shah Devavrat
Wornell Gregory
No associations
LandOfFree
Adaptive Alternating Minimization Algorithms does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Adaptive Alternating Minimization Algorithms, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Adaptive Alternating Minimization Algorithms will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-721690