New error bounds for Solomonoff prediction (2001) [18 citations — 10 self]
|
Abstract:
Solomono sequence prediction is a scheme to predict digits of (binary) strings without knowing the underlying probability distribution. We call a prediction scheme informed, when it knows the true probability distribution of the sequence. Several new relations between universal Solomono sequence prediction and informed prediction and general probabilistic prediction schemes will be proved. Among others, they show that the number of errors in Solomono prediction is nite for computable distributions, if nite in the informed case. Deterministic variants will also be studied. The most interesting result is that the deterministic variant of Solomono prediction is optimal compared to any other probabilistic or deterministic prediction scheme apart from additive square root corrections only. This makes it well suited even for dicult prediction problems, where it does not suce when the number of errors is minimal to within some factor greater than one. Solomono's original bound and the ones presented here complement each other in a useful way.
