Sciweavers

10 search results - page 1 / 2
» Monotone Conditional Complexity Bounds on Future Prediction ...
Sort
View
ALT
2005
Springer
14 years 1 months ago
Monotone Conditional Complexity Bounds on Future Prediction Errors
We bound the future loss when predicting any (computably) stochastic sequence online. Solomonoff finitely bounded the total deviation of his universal predictor M from the true ...
Alexey V. Chernov, Marcus Hutter
DAGSTUHL
2006
13 years 6 months ago
Complexity Monotone in Conditions and Future Prediction Errors
We bound the future loss when predicting any (computably) stochastic sequence online. Solomonoff finitely bounded the total deviation of his universal predictor M from the true dis...
Alexey V. Chernov, Marcus Hutter, Jürgen Schm...
CORR
2007
Springer
169views Education» more  CORR 2007»
13 years 4 months ago
Algorithmic Complexity Bounds on Future Prediction Errors
We bound the future loss when predicting any (computably) stochastic sequence online. Solomonoff finitely bounded the total deviation of his universal predictor M from the true d...
Alexey V. Chernov, Marcus Hutter, Jürgen Schm...
ATAL
2008
Springer
13 years 6 months ago
Approximate predictive state representations
Predictive state representations (PSRs) are models that represent the state of a dynamical system as a set of predictions about future events. The existing work with PSRs focuses ...
Britton Wolfe, Michael R. James, Satinder P. Singh
ML
2000
ACM
103views Machine Learning» more  ML 2000»
13 years 4 months ago
Nonparametric Time Series Prediction Through Adaptive Model Selection
We consider the problem of one-step ahead prediction for time series generated by an underlying stationary stochastic process obeying the condition of absolute regularity, describi...
Ron Meir