On Universal Prediction and Bayesian Confirmation

Details On Universal Prediction and Bayesian Confirmation On Universal Prediction and Bayesian Confirmation

2007-09-11

arxiv.org/abs/0709.1516v1

Theoretical Computer Science, 384 (2007) pages 33-48

Mathematics

Statistics Theory

24 pages

Scientific paper

The Bayesian framework is a well-studied and successful framework for inductive reasoning, which includes hypothesis testing and confirmation, parameter estimation, sequence prediction, classification, and regression. But standard statistical guidelines for choosing the model class and prior are not always available or fail, in particular in complex situations. Solomonoff completed the Bayesian framework by providing a rigorous, unique, formal, and universal choice for the model class and the prior. We discuss in breadth how and in which sense universal (non-i.i.d.) sequence prediction solves various (philosophical) problems of traditional Bayesian sequence prediction. We show that Solomonoff's model possesses many desirable properties: Strong total and weak instantaneous bounds, and in contrast to most classical continuous prior densities has no zero p(oste)rior problem, i.e. can confirm universal hypotheses, is reparametrization and regrouping invariant, and avoids the old-evidence and updating problem. It even performs well (actually better) in non-computable environments.

Affiliated with

Also associated with

No associations

Rating

On Universal Prediction and Bayesian Confirmation 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 On Universal Prediction and Bayesian Confirmation, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and On Universal Prediction and Bayesian Confirmation will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-391493