Computer Science – Learning
Scientific paper
2001-06-15
Lecture Notes in Artificial Intelligence (LNAI 2167), Proc. 12th Eurpean Conf. on Machine Learning (ECML) (2001) 239-250
Computer Science
Learning
11 LaTeX pages
Scientific paper
Solomonoff's uncomputable universal prediction scheme $\xi$ allows to predict the next symbol $x_k$ of a sequence $x_1...x_{k-1}$ for any Turing computable, but otherwise unknown, probabilistic environment $\mu$. This scheme will be generalized to arbitrary environmental classes, which, among others, allows the construction of computable universal prediction schemes $\xi$. Convergence of $\xi$ to $\mu$ in a conditional mean squared sense and with $\mu$ probability 1 is proven. It is shown that the average number of prediction errors made by the universal $\xi$ scheme rapidly converges to those made by the best possible informed $\mu$ scheme. The schemes, theorems and proofs are given for general finite alphabet, which results in additional complications as compared to the binary case. Several extensions of the presented theory and results are outlined. They include general loss functions and bounds, games of chance, infinite alphabet, partial and delayed prediction, classification, and more active systems.
No associations
LandOfFree
Convergence and Error Bounds for Universal Prediction of Nonbinary Sequences 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 Convergence and Error Bounds for Universal Prediction of Nonbinary Sequences, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Convergence and Error Bounds for Universal Prediction of Nonbinary Sequences will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-174499