Sciweavers

Share
warning: Creating default object from empty value in /var/www/modules/taxonomy/taxonomy.module on line 1416.
JMLR
2010
129views more  JMLR 2010»
11 years 8 months ago
On Finding Predictors for Arbitrary Families of Processes
The problem is sequence prediction in the following setting. A sequence x1, . . . , xn, . . . of discrete-valued observations is generated according to some unknown probabilistic ...
Daniil Ryabko
CORR
2006
Springer
121views Education» more  CORR 2006»
11 years 9 months ago
On the Foundations of Universal Sequence Prediction
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...
Marcus Hutter
ICML
2010
IEEE
11 years 10 months ago
Forgetting Counts: Constant Memory Inference for a Dependent Hierarchical Pitman-Yor Process
We propose a novel dependent hierarchical Pitman-Yor process model for discrete data. An incremental Monte Carlo inference procedure for this model is developed. We show that infe...
Nicholas Bartlett, David Pfau, Frank Wood
AGI
2008
11 years 11 months ago
Adversarial Sequence Prediction
Sequence prediction is a key component of intelligence. This can be extended to define a game between intelligent agents. An analog of a result of Legg shows that this game is a co...
Bill Hibbard
COLT
2003
Springer
12 years 2 months ago
Sequence Prediction Based on Monotone Complexity
This paper studies sequence prediction based on the monotone Kolmogorov complexity Km=−log m, i.e. based on universal deterministic/one-part MDL. m is extremely close to Solomon...
Marcus Hutter
COLT
2004
Springer
12 years 2 months ago
Convergence of Discrete MDL for Sequential Prediction
We study the properties of the Minimum Description Length principle for sequence prediction, considering a two-part MDL estimator which is chosen from a countable class of models....
Jan Poland, Marcus Hutter
ATAL
2005
Springer
12 years 3 months ago
Rapid on-line temporal sequence prediction by an adaptive agent
Robust sequence prediction is an essential component of an intelligent agent acting in a dynamic world. We consider the case of near-future event prediction by an online learning ...
Steven Jensen, Daniel Boley, Maria L. Gini, Paul R...

Publication
404views
12 years 6 months ago
Bayesian variable order Markov models.
We present a simple, effective generalisation of variable order Markov models to full online Bayesian estimation. The mechanism used is close to that employed in context tree wei...
Christos Dimitrakakis
books