arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2303.11536cs.LGcs.AIcs.CVmath.STstat.MLstat.TH
收藏

不定概率论

Indeterminate Probability Theory

AI Lab, United Automotive Electronic Systems Co., Ltd.(人工智能实验室,联合汽车电子系统有限公司)

Tao Yang, Chuang Liu, Xiaofeng Ma, Weijia Lu, Ning Wu, Bingyang Li, Zhifei Yang, Peng Liu, Lin Sun, Xiaodong Zhang, Can Zhang

AI总结:

本文提出不定概率论(IPT),通过观察者中心框架和三个独立性公理,为任意复杂联合分布推导闭式解,并在高维建模中验证其有效性,且与经典概率论一致。

摘要:

复杂的连续或混合联合分布(例如,P(Y | z_1, z_2, ..., z_N))通常缺乏闭式解,常常需要近似方法如MCMC。本文提出了不定概率论(Indeterminate Probability Theory, IPT),其贡献如下:(1)一个以观察者为中心的框架,其中实验结果被表示为结合了真实值与观察误差的分布;(2)引入了三个独立性候选公理,使得两阶段概率推断框架成为可能;(3)在该框架下推导出任意复杂联合分布的闭式解。不定概率神经网络(IPNN)模型和非神经网络的多元时间序列预测应用均证明了IPT在高维分布建模中的有效性,并成功验证了高达1000维的情况。重要的是,IPT与经典概率论一致,并在观察误差趋近于零的极限情况下包含了频率学派的方程。

英文摘要:

Complex continuous or mixed joint distributions (e.g., P(Y | z_1, z_2, ..., z_N)) generally lack closed-form solutions, often necessitating approximations such as MCMC. This paper proposes Indeterminate Probability Theory (IPT), which makes the following contributions: (1) An observer-centered framework in which experimental outcomes are represented as distributions combining ground truth with observation error; (2) The introduction of three independence candidate axioms that enable a two-phase probabilistic inference framework; (3) The derivation of closed-form solutions for arbitrary complex joint distributions under this framework. Both the Indeterminate Probability Neural Network (IPNN) model and the non-neural multivariate time series forecasting application demonstrate IPT's effectiveness in modeling high-dimensional distributions, with successful validation up to 1000 dimensions. Importantly, IPT is consistent with classical probability theory and subsumes the frequentist equation in the limit of vanishing observation error.

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。

↑