几何Jensen-Shannon分歧的两种类型
1Sony Computer Science Laboratories, Tokyo 141-0022, Japan.
Entropy (Basel, Switzerland)
|September 27, 2025
概括
研究人员为正密度引入了扩展的几何Jensen-Shannon分歧 (G-JSD),为机器学习和信息科学提供了一个新的工具. 这种扩展的G-JSD提供了比标准G-JSD更普遍的方法,在高斯分布分析中有应用.
科学领域:
- 信息理论 信息理论
- 机器学习 机器学习
- 数学统计学数学统计学
背景情况:
- 几何Jensen-Shannon分歧 (G-JSD) 由于其对高斯分布的封闭形式解决方案而被广泛使用.
- 现有的G-JSD定义存在局限性,特别是在正密度和几何混合物的规范化方面.
研究的目的:
- 引入一种新的,扩展的几何詹森-香农分歧 (扩展的G-JSD),适用于正密度和尺度.
- 分析扩展G-JSD,标准G-JSD和其他差异测量方法 (如杰弗里差异和巴塔卡里亚距离) 之间的关系.
- 探索扩展G-JSD的特性和应用,包括其与高斯分布的行为以及其作为规范化技术的潜力.
主要方法:
- 为正密度的几何Jensen-Shannon分歧开发了一个新的定义,称为扩展G-JSD,用于正密度.
- 对于多变量高斯分布的G-JSD和扩展的G-JSD的衍生闭式公式.
- 研究了扩展G-JSD的特性,包括其作为f-分歧的分类及其信息几何特征.
- 探索了使用投影性γ-分歧的蒙特卡洛估计和近似.
主要成果:
- 扩展的G-JSD是为正密度定义的,没有规范化几何混合物,将标准G-JSD.
- 扩展G-JSD和G-JSD之间的差距的明确表达式为概率密度提供.
- 无论是G-JSD还是扩展的G-JSD都可以使用杰弗里斯分歧和巴塔卡里亚距离/系数来表达.
- 扩展的G-JSD是一个f-分歧,满足信息单调性和不变性属性.
- 对于多变量高斯分布的闭式公式,对于这两种差异都得出了.
- 与标准詹森-香农分歧的平方根不同,G-JSD和扩展的G-JSD的平方根不构成公尺距离.
结论:
- 扩展的G-JSD为正密度和正量提供了一个更具多样性和通用性的分歧测量方法.
- 衍生的公式和属性有助于实际应用,特别是机器学习中的高斯分布.
- 这项研究强调了G-JSDs作为普通JSD的规范化的可解释性.
关键词:
巴塔查里亚距离 巴塔查里亚距离切尔诺夫信息 切尔诺夫信息杰弗里斯的分歧.詹森香农的分歧.塔内贾的分歧.指数式的家族是指数式的家族.f-分歧 f-分歧几何混合物 几何混合物信息的单调性 单调性预测的 γ-分歧.准算术意味着准算术.可分离的分歧分离.总变化距离的总变化距离更多相关视频
15:07VDJ-Seq: Deep Sequencing Analysis of Rearranged Immunoglobulin Heavy Chain Gene to Reveal Clonal Evolution Patterns of B Cell Lymphoma
Published on: December 28, 2015
27.2K
11:00Experimental Investigation of Secondary Flow Structures Downstream of a Model Type IV Stent Failure in a 180° Curved Artery Test Section
Published on: July 19, 2016
12.0K
相关概念视频
Divergence and Curl
3.1K
The divergence of a vector field at a point is the net outward flow of the flux out of a small volume through a closed surface enclosing the volume, as the volume tends to zero. More practically, divergence measures how much a vector field spreads out or diverges from a given point. For an outgoing flux, conventionally, the divergence is positive. The diverging point is often called the "source" of the field. Meanwhile, the negative divergence of a vector field at a point means that the vector...
3.1K
Divergence and Stokes' Theorems
3.5K
The divergence and Stokes' theorems are a variation of Green's theorem in a higher dimension. They are also a generalization of the fundamental theorem of calculus. The divergence theorem and Stokes' theorem are in a way similar to each other; The divergence theorem relates to the dot product of a vector, while Stokes' theorem relates to the curl of a vector. Many applications in physics and engineering make use of the divergence and Stokes' theorems, enabling us to write...
3.5K
Types of Skewness
17.5K
If the frequency distribution of a data set is more inclined towards smaller or larger values, the distribution is said to be skewed. If data values are skewed to the right, then the distribution is called positively skewed. Conversely, if the plot is skewed to the left, the distribution is called negatively skewed.
For instance, in the middle of a pandemic, the geographical distribution of vaccine coverage may be positively skewed towards populations in the global north countries. However,...
For instance, in the middle of a pandemic, the geographical distribution of vaccine coverage may be positively skewed towards populations in the global north countries. However,...
17.5K
Geometric Mean
3.9K
The mean is a measure of the central tendency of a data set. In some data sets, the data is inherently multiplicative, and the arithmetic mean is not useful. For example, the human population multiplies with time, and so does the credit amount of financial investment, as the interest compounds over successive time intervals.
In cases of multiplicative data, the geometric mean is used for statistical analysis. First, the product of all the elements is taken. Then, if there are n elements in the...
In cases of multiplicative data, the geometric mean is used for statistical analysis. First, the product of all the elements is taken. Then, if there are n elements in the...
3.9K
Second Uniqueness Theorem
2.6K
Consider a region consisting of several individual conductors with a definite charge density in the region between these conductors. The second uniqueness theorem states that if the total charge on each conductor and the charge density in the in-between region are known, then the electric field can be uniquely determined.
In contrast, consider that the electric field is non-unique and apply Gauss's law in divergence form in the region between the conductors and the integral form to the surface...
In contrast, consider that the electric field is non-unique and apply Gauss's law in divergence form in the region between the conductors and the integral form to the surface...
2.6K
Divergence and Curl of Electric Field
7.1K
The divergence of a vector is a measure of how much the vector spreads out (diverges) from a point. For example, an electric field vector diverges from the positive charge and converges at the negative charge. The divergence of an electric field is derived using Gauss's law and is equal to the charge density divided by the permittivity of space. Mathematically, it is expressed as
7.1K
