Universal probability-free prediction
Ann. Math. Artif. Intell.(2017)
摘要
We construct universal prediction systems in the spirit of Popper’s falsifiability and Kolmogorov complexity and randomness. These prediction systems do not depend on any statistical assumptions (but under the IID assumption they dominate, to within the usual accuracy, conformal prediction). Our constructions give rise to a theory of algorithmic complexity and randomness of time containing analogues of several notions and results of the classical theory of Kolmogorov complexity and randomness.
更多查看译文
关键词
Conformal prediction,Prediction systems,Probability-free learning,Universal prediction,68Q30,60G25,62M20,68Q32,68T05,62G15
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络