Field theories for learning probability distributions

被引：82

作者：

Bialek, W ^{[1
]}

Callan, CG ^{[1
]}

Strong, SP ^{[1
]}

机构：

[1] PRINCETON UNIV, DEPT PHYS, PRINCETON, NJ 08544 USA

来源：

PHYSICAL REVIEW LETTERS | 1996年 / 77卷 / 23期

关键词：

D O I：

10.1103/PhysRevLett.77.4693

中图分类号：

O4 [物理学];

学科分类号：

0702 ;

摘要：

Imagine being shown N samples of random variables drawn independently from the same distribution. What can you say about the distribution? In general, of course, the answer is nothing, unless you have some prior notions about what to expect. From a Bayesian point of view one needs an a priori distribution on the space of possible probability distributions, which defines st scalar field theory. In one dimension, free field theory with a normalization constraint provides a tractable formulation of the problem, and we discuss generalizations to higher dimensions.

引用

页码：4693 / 4697

页数：5

共 11 条

[1]

BALASUBRAMANIAN V, IN PRESS NEURAL COMP

[2] MINIMUM COMPLEXITY DENSITY-ESTIMATION [J].