id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
work_mr277dtjk5cjlaldsrhnizxngq	Tom F. Sterkenburg	Solomonoff Prediction and Occam's Razor	2016	18	.pdf	application/pdf	10026	755	56	Algorithmic information theory gives an idealized notion of compressibility, that is often presented as an objective measure of simplicity. inductive assumption, that by a basic property of Bayesian prediction methods entails reliability under that very same assumption – leaving the conclusion of the a representation theorem that bridges Solomonoff's predictors and Bayesian prediction. machines, we have an infinite class of algorithmic probability predictors. denote Q := {QU}U , the class of algorithmic probability predictors via all universal We can prove that any Bayesian predictor, operating under the inductive assumption of S, is reliable under the assumption that the data is indeed generated probability predictors, and a particular class of Bayesian mixtures, the effective assumption of an i.i.d. source; and Theorem 6 shows that the algorithmic probability predictors operate under the inductive assumption of an effective source. Solomonoff's algorithmic probability predictors are precisely the Bayesian predictors operating under the inductive assumption of effectiveness.	./cache/work_mr277dtjk5cjlaldsrhnizxngq.pdf	./txt/work_mr277dtjk5cjlaldsrhnizxngq.txt