Complexity Monotone in Conditions and Future Prediction Errors

13 years 5 months ago

Download drops.dagstuhl.de

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 distribution

Alexey V. Chernov, Marcus Hutter, Jürgen Schm

Real-time Traffic

DAGSTUHL 2006 | DAGSTUHL 2007 | Future Loss | Stochastic Sequence Online | Total Deviation |

claim paper

» Algorithmic Complexity Bounds on Future Prediction Errors

» Avoiding Latent Design Conditions Using UI Discovery Tools

» Approximate predictive state representations

» Minimizing the Effect of Process Mismatch in a Neuromorphic System Using SpikeTimingDepend...

» Channel Prediction Heuristics for Adaptive Modulation in WLAN

» Adaptive Observation Strategies for Forecast Error Minimization

» On the prediction of the evolution of libre software projects

» Load prediction models in webbased systems

Post Info
More Details (n/a)

Added	30 Oct 2010
Updated	30 Oct 2010
Type	Conference
Year	2006
Where	DAGSTUHL
Authors	Alexey V. Chernov, Marcus Hutter, Jürgen Schmidhuber

Comments (0)

Sciweavers

Complexity Monotone in Conditions and Future Prediction Errors

DAGSTUHL 2006 | DAGSTUHL 2007 | Future Loss | Stochastic Sequence Online | Total Deviation |

Explore & Download

Productivity Tools

Document Tools

Image Tools

Sciweavers