论文标题
所罗门诺夫预测的难题
A Dilemma for Solomonoff Prediction
论文作者
论文摘要
所罗门诺夫预测的框架将先前的概率分配给假设与其kolmogorov复杂性成反比。有两个众所周知的问题。首先，Solomonoff先验是相对于通用图灵机的选择。其次，Solomonoff先验是不可计算的。但是，对这两个问题都有回应。不同的Solomonoff先生会收敛于越来越多的数据。此外，对Solomonoff先验还有可计算的近似值。我认为这两个响应之间存在张力。这是因为对所罗诺夫预测的可计算近似值并不总是收敛。
The framework of Solomonoff prediction assigns prior probability to hypotheses inversely proportional to their Kolmogorov complexity. There are two well-known problems. First, the Solomonoff prior is relative to a choice of Universal Turing machine. Second, the Solomonoff prior is not computable. However, there are responses to both problems. Different Solomonoff priors converge with more and more data. Further, there are computable approximations to the Solomonoff prior. I argue that there is a tension between these two responses. This is because computable approximations to Solomonoff prediction do not always converge.
