Speed prior

The speed prior is a complexity measure similar to Kolmogorov complexity, except that it is based on computation speed as well as program length. ^[1] The speed prior complexity of a program is its size in bits plus the logarithm of the maximum time we are willing to run it to get a prediction.

When compared to traditional measures, use of the Speed. Prior has the disadvantage of leading to less optimal predictions, and the advantage of providing computable predictions.

See also

• Computational complexity theory
• Inductive inference
• Minimum message length
• Minimum description length

References

1. Schmidhuber, J. (2002) The Speed Prior: A New Simplicity Measure Yielding Near-Optimal Computable Predictions. In J. Kivinen and R. H. Sloan, editors, Proceedings of the 15th Annual Conference on Computational Learning Theory (COLT 2002). Lecture Notes in Artificial Intelligence, pages 216--228. Springer.

External links

• Speed Prior web site