Variants of Solomonoff induction

From Machinelearning
Revision as of 02:46, 31 March 2019 by IssaRice (talk | contribs)

This page lists some variants of Solomonoff induction.

For determinism, I think "deterministic" is the same as "Solomonoff prior" and "stochastic" is the same as "universal mixture".

For discrete vs continuous, I think this just means whether the prior we define is over finite strings or over infinite sequences (where we want to know the probability of an infinite sequence starting with a given finite string).

Source Formula Determinism Type of machine used Discrete vs continuous
LessWrong Wiki[1] where is the set of self-delimiting programs Deterministic Page doesn't say, but uses self-delimiting programs and it's discrete, so prefix Turing machine? Discrete because the output string is finite
Scholarpedia discrete universal a priori probability[2] deterministic? prefix Turing machine discrete
Scholarpedia continuous universal a priori probability[2] deterministic? Monotone Turing machine Continuous

References

  1. https://wiki.lesswrong.com/wiki/Solomonoff_induction
  2. 2.0 2.1 Marcus Hutter; Shane Legg; Paul M.B. Vitanyi. "Algorithmic probability". 2007.