by Daniil Ryabko, Marcus Hutter
http://daniil.ryabko.net/pq.pdf
Add To MetaCart
Abstract:
Suppose we are given two probability measures on the set of one-way infinite finite-alphabet sequences and consider the question when one of the measures predicts the other, that is, when conditional probabilities converge (in a certain sense) when one of the measures is chosen to generate the sequence. This question may be considered a refinement of the problem of sequence prediction in its most general formulation: for a given class of probability measures, does there exist a measure which predicts all of the measures in the class? To address this problem, we find some conditions on local absolute continuity which are sufficient for prediction and which generalize several different notions which are known to be sufficient for prediction. We also formulate some open questions to outline a direction for finding the conditions
Citations
|
109
|
The complexity of finite objects and the development of the concepts of information and randomness by means of the theory of algorithms,” Russ
– Zvonkin, Levin
- 1970
|
|
79
|
Complexity-based induction systems: comparisons and convergence theorems
– Solomonoff
- 1978
|
|
48
|
Universal Artificial Intelligence: Sequential Decisions based on Algorithmic Probability
– Hutter
|
|
27
|
Merging of opinions with increasing information
– Blackwell, Dubins
- 1962
|
|
26
|
A formal theory of inductive inference: Part 1 and 2
– Solomonoff
- 1964
|
|
24
|
Prediction of random sequences and universal coding
– Ryabko
- 1988
|
|
4
|
On the foundations of universal sequence prediction
– Hutter
- 2006
|
|
4
|
Bayesian representation of stochastic processes under learning: De finetti revisited
– Jackson, Kalai, et al.
- 1999
|
|
2
|
Universal codes as a basis for time series testing. Statistical Methodology, To appear, available online
– Ryabko, Astola
- 2006
|
|
1
|
Bayesian forecasting. Discussion paper 998
– Kalai, Lehrer
- 1992
|
|
1
|
Asymptotic learnability of reinforcement problems with arbitrary dependence
– Ryabko, Hutter
- 2006
|
