General loss bounds for universal sequence prediction
The Bayesian framework is ideally suited for induction problems. The probability of observing xk at time k, given past observations x1...xk-1 can be computed with Bayes' rule if the true distribution µ of the sequences x1x2x3... is known. The problem, however, is that in many cases one does not even have a reasonable estimate of the true distribution. In order to overcome this problem a universal distribution ß is defined as a weighted sum of distributions µi in M, where M is any countable set...[Show more]
|Collections||ANU Research Publications|
Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.