arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2404.17023cs.ITcs.LGmath.IT
收藏

使用最大熵编码的分布外检测

Out-of-Distribution Detection using Maximum Entropy Coding

University of Hawaii at Manoa(夏威夷大学马诺阿分校);John A. Burns School of Medicine, University of Hawaii(夏威夷大学约翰·A·伯恩斯医学院)

Mojtaba Abolfazli, Mohammad Zaeri Amirani, Anders Høst-Madsen, June Zhang, Andras Bratincsak

AI总结:

本文提出一种基于最大熵编码的分布外检测方法,通过统计量关联最大熵分布计算总码长,并结合双向生成网络在潜空间转换未知真实数据,在多数异常检测实验中表现优于其他生成神经网络方法。

摘要:

给定默认分布$P$和一组测试数据$x^M=\{x_1,x_2,\ldots,x_M\}$,本文旨在回答$x^M$是否可能由$P$生成的问题。对于离散分布,Kolmogorov-Martin-Löf随机性原则上给出了确切答案。本文旨在将其推广至连续分布。我们考虑一组统计量$T_1(x^M),T_2(x^M),\ldots$。为每个统计量关联其最大熵分布及通用源编码器。最大熵分布随后被组合以给出总码长,并与$-\log P(x^M)$进行比较。我们证明该方法满足若干理论性质。对于真实世界数据,$P$通常未知。我们利用双向生成网络将数据转换为潜空间中的标准分布,并在该空间应用最大熵编码。我们将该方法与同样使用生成神经网络检测异常的方法进行比较。在多数情况下,我们的结果展现出更优的性能。

英文摘要:

Given a default distribution $P$ and a set of test data $x^M=\{x_1,x_2,\ldots,x_M\}$ this paper seeks to answer the question if it was likely that $x^M$ was generated by $P$. For discrete distributions, the definitive answer is in principle given by Kolmogorov-Martin-Löf randomness. In this paper we seek to generalize this to continuous distributions. We consider a set of statistics $T_1(x^M),T_2(x^M),\ldots$. To each statistic we associate its maximum entropy distribution and with this a universal source coder. The maximum entropy distributions are subsequently combined to give a total codelength, which is compared with $-\log P(x^M)$. We show that this approach satisfied a number of theoretical properties. For real world data $P$ usually is unknown. We transform data into a standard distribution in the latent space using a bidirectional generate network and use maximum entropy coding there. We compare the resulting method to other methods that also used generative neural networks to detect anomalies. In most cases, our results show better performance.

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。

↑