Indeterminate Probability Theory
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2023
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908415168610304 |
|---|---|
| author | Yang, Tao Liu, Chuang Ma, Xiaofeng Lu, Weijia Wu, Ning Li, Bingyang Yang, Zhifei Liu, Peng Sun, Lin Zhang, Xiaodong Zhang, Can |
| author_facet | Yang, Tao Liu, Chuang Ma, Xiaofeng Lu, Weijia Wu, Ning Li, Bingyang Yang, Zhifei Liu, Peng Sun, Lin Zhang, Xiaodong Zhang, Can |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2303_11536 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Indeterminate Probability Theory Yang, Tao Liu, Chuang Ma, Xiaofeng Lu, Weijia Wu, Ning Li, Bingyang Yang, Zhifei Liu, Peng Sun, Lin Zhang, Xiaodong Zhang, Can Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition Statistics Theory 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. |
| title | Indeterminate Probability Theory |
| topic | Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition Statistics Theory |
| url | https://arxiv.org/abs/2303.11536 |