arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1604.03343cs.LGstat.ML
收藏

速度先验的损失界和时间复杂度

Loss Bounds and Time Complexity for Speed Priors

Daniel Filan, Marcus Hutter, Jan Leike

摘要:

本文首次建立了速度先验的预测性能及其计算复杂性。速度先验本质上是一种概率分布,它将低概率放在无法有效计算的字符串上。我们提出了一个变种,原来的速度先验(Schmidhuber,2002年),并表明我们的先验可以预测序列的概率措施,估计在多项式时间。我们的速度先验在双指数时间内是可计算的,但在多项式时间内是不可计算的。在一个多项式时间可计算序列上,我们的速度先验可以在指数时间内计算。我们表现出更好的上复杂性界Schmidhuber的速度在相同的条件下,之前,它预测的确定性序列是可计算的多项式时间,但是,我们也表明,它是不可计算的多项式时间,其预测性能的随机序列的问题仍然是开放的。

英文摘要:

This paper establishes for the first time the predictive performance of speed priors and their computational complexity. A speed prior is essentially a probability distribution that puts low probability on strings that are not efficiently computable. We propose a variant to the original speed prior (Schmidhuber, 2002), and show that our prior can predict sequences drawn from probability measures that are estimable in polynomial time. Our speed prior is computable in doubly-exponential time, but not in polynomial time. On a polynomial time computable sequence our speed prior is computable in exponential time. We show better upper complexity bounds for Schmidhuber's speed prior under the same conditions, and that it predicts deterministic sequences that are computable in polynomial time; however, we also show that it is not computable in polynomial time, and the question of its predictive properties for stochastic sequences remains open.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑