Characterizing predictable classes of processes

Details Characterizing predictable classes of processes Characterizing predictable classes of processes

2009-05-27

arxiv.org/abs/0905.4341v1

Computer Science

Artificial Intelligence

Scientific paper

The problem is sequence prediction in the following setting. A sequence $x_1,...,x_n,...$ of discrete-valued observations is generated according to some unknown probabilistic law (measure) $\mu$. After observing each outcome, it is required to give the conditional probabilities of the next observation. The measure $\mu$ belongs to an arbitrary class $\C$ of stochastic processes. We are interested in predictors $\rho$ whose conditional probabilities converge to the "true" $\mu$-conditional probabilities if any $\mu\in\C$ is chosen to generate the data. We show that if such a predictor exists, then a predictor can also be obtained as a convex combination of a countably many elements of $\C$. In other words, it can be obtained as a Bayesian predictor whose prior is concentrated on a countable set. This result is established for two very different measures of performance of prediction, one of which is very strong, namely, total variation, and the other is very weak, namely, prediction in expected average Kullback-Leibler divergence.

Affiliated with

Also associated with

No associations

Rating

Characterizing predictable classes of processes 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 Characterizing predictable classes of processes, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Characterizing predictable classes of processes will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-527336