Notes on the Dirichlet Distribution and Dirichlet Process
Notes on the Dirichlet Distribution and Dirichlet Process
%matplotlib inline
Note: I wrote this post in an IPython notebook. It might be rendered better on NBViewer.
Dirichlet Distribution
The symmetric Dirichlet distribution (DD) can be considered a distribution of distributions. Each sample from the DD is acategorial distribution over K categories. It is parameterized G0, a distribution over K categories and α, a scale factor.
The expected value of the DD is G0. The variance of the DD is a function of the scale factor. When α is large, samples from DD(α⋅G0) will be very close to G0. When α is small, samples will vary more widely.
We demonstrate below by setting G0=[.2,.2,.6] and varying α from 0.1 to 1000. In each case, the mean of the samples is roughly G0, but the standard deviation is decreases as α increases.
import numpy as np
from scipy.stats import dirichlet
np.set_printoptions(precision=2) def stats(scale_factor, G0=[.2, .2, .6], N=10000):
samples = dirichlet(alpha = scale_factor * np.array(G0)).rvs(N)
print " alpha:", scale_factor
print " element-wise mean:", samples.mean(axis=0)
print "element-wise standard deviation:", samples.std(axis=0)
print for scale in [0.1, 1, 10, 100, 1000]:
stats(scale)
alpha: 0.1
element-wise mean: [ 0.2 0.2 0.6]
element-wise standard deviation: [ 0.38 0.38 0.47] alpha: 1
element-wise mean: [ 0.2 0.2 0.6]
element-wise standard deviation: [ 0.28 0.28 0.35] alpha: 10
element-wise mean: [ 0.2 0.2 0.6]
element-wise standard deviation: [ 0.12 0.12 0.15] alpha: 100
element-wise mean: [ 0.2 0.2 0.6]
element-wise standard deviation: [ 0.04 0.04 0.05] alpha: 1000
element-wise mean: [ 0.2 0.2 0.6]
element-wise standard deviation: [ 0.01 0.01 0.02]
Dirichlet Process
The Dirichlet Process can be considered a way to generalizethe Dirichlet distribution. While the Dirichlet distribution is parameterized by a discrete distribution G0 and generates samples that are similar discrete distributions, the Dirichlet process is parameterized by a generic distribution H0 and generates samples which are distributions similar to H0. The Dirichlet process also has a parameter α that determines how similar how widely samples will vary from H0.
We can construct a sample H (recall that H is a probability distribution) from a Dirichlet process DP(αH0) by drawing a countably infinite number of samples θk from H0) and setting:
where the πk are carefully chosen weights (more later) that sum to 1. (δ is the Dirac delta function.)
H, a sample from DP(αH0), is a probability distributionthat looks similar to H0 (also a distribution). In particular, His a discrete distribution that takes the value θk with probability πk. This sampled distribution H is a discrete distribution even if H0 has continuous support; the support ofH is a countably infinite subset of the support H0.
The weights (pk values) of a Dirichlet process sample related the Dirichlet process back to the Dirichlet distribution.
Gregor Heinrich writes:
The defining property of the DP is that its samples have weights πk and locations θk distributed in such a way that when partitioning S(H) into finitely many arbitrary disjoint subsets S1,…,Sj J<∞, the sums of the weights πk in each of these J subsets are distributed according to a Dirichlet distribution that is parameterized by α and a discrete base distribution (likeG0) whose weights are equal to the integrals of the base distribution H0 over the subsets Sn.
As an example, Heinrich imagines a DP with a standard normal base measure H0∼N(0,1). Let H be a sample fromDP(H) and partition the real line (the support of a normal distribution) as S1=(−∞,−1], S2=(−1,1], and S3=(1,∞] then
where H(Sn) be the sum of the πk values whose θk lie in Sn.
These Sn subsets are chosen for convenience, however similar results would hold for any choice of Sn. For any sample from a Dirichlet process, we can construct a sample from a Dirichletdistribution by partitioning the support of the sample into a finite number of bins.
There are several equivalent ways to choose the πk so that this property is satisfied: the Chinese restaurant process, the stick-breaking process, and the Pólya urn scheme.
To generate {πk} according to a stick-breaking process we define βk to be a sample from Beta(1,α). π1 is equal to β1. Successive values are defined recursively as
Thus, if we want to draw a sample from a Dirichlet distribution, we could, in theory, sample an infinite number of θk values from the base distribution H0, an infinite number of βk values from the Beta distribution. Of course, sampling an infinite number of values is easier in theory than in practice.
However, by noting that the πk values are positive values summing to 1, we note that, in expectation, they must get increasingly small as k→∞. Thus, we can reasonably approximate a sample H∼DP(αH0) by drawing enoughsamples such that ∑Kk=1πk≈1.
We use this method below to draw approximate samples from several Dirichlet processes with a standard normal (N(0,1)) base distribution but varying α values.
Recall that a single sample from a Dirichlet process is a probability distribution over a countably infinite subset of the support of the base measure.
The blue line is the PDF for a standard normal. The black lines represent the θk and πk values; θk is indicated by the position of the black line on the x-axis; πk is proportional to the height of each line.
We generate enough πk values are generated so their sum is greater than 0.99. When α is small, very few θk's will have corresponding πk values larger than 0.01. However, as αgrows large, the sample becomes a more accurate (though still discrete) approximation of N(0,1).
import matplotlib.pyplot as plt
from scipy.stats import beta, norm def dirichlet_sample_approximation(base_measure, alpha, tol=0.01):
betas = []
pis = []
betas.append(beta(1, alpha).rvs())
pis.append(betas[0])
while sum(pis) < (1.-tol):
s = np.sum([np.log(1 - b) for b in betas])
new_beta = beta(1, alpha).rvs()
betas.append(new_beta)
pis.append(new_beta * np.exp(s))
pis = np.array(pis)
thetas = np.array([base_measure() for _ in pis])
return pis, thetas def plot_normal_dp_approximation(alpha):
plt.figure()
plt.title("Dirichlet Process Sample with N(0,1) Base Measure")
plt.suptitle("alpha: %s" % alpha)
pis, thetas = dirichlet_sample_approximation(lambda: norm().rvs(), alpha)
pis = pis * (norm.pdf(0) / pis.max())
plt.vlines(thetas, 0, pis, )
X = np.linspace(-4,4,100)
plt.plot(X, norm.pdf(X)) plot_normal_dp_approximation(.1)
plot_normal_dp_approximation(1)
plot_normal_dp_approximation(10)
plot_normal_dp_approximation(1000)
Often we want to draw samples from a distribution sampled from a Dirichlet process instead of from the Dirichlet process itself. Much of the literature on the topic unhelpful refers to this as sampling from a Dirichlet process.
Fortunately, we don't have to draw an infinite number of samples from the base distribution and stick breaking process to do this. Instead, we can draw these samples as they are needed.
Suppose, for example, we know a finite number of the θk and πk values for a sample H∼Dir(αH0). For example, we know
To sample from H, we can generate a uniform random unumber between 0 and 1. If u is less than 0.5, our sample is 0.1. If 0.5<=u<0.8, our sample is −0.5. If u>=0.8, our sample (from H will be a new sample θ3 from H0. At the same time, we should also sample and store π3. When we draw our next sample, we will again draw u∼Uniform(0,1) but will compare against π1,π2, AND π3.
The class below will take a base distribution H0 and α as arguments to its constructor. The class instance can then be called to generate samples from H∼DP(αH0).
from numpy.random import choice class DirichletProcessSample():
def __init__(self, base_measure, alpha):
self.base_measure = base_measure
self.alpha = alpha self.cache = []
self.weights = []
self.total_stick_used = 0. def __call__(self):
remaining = 1.0 - self.total_stick_used
i = DirichletProcessSample.roll_die(self.weights + [remaining])
if i is not None and i < len(self.weights) :
return self.cache[i]
else:
stick_piece = beta(1, self.alpha).rvs() * remaining
self.total_stick_used += stick_piece
self.weights.append(stick_piece)
new_value = self.base_measure()
self.cache.append(new_value)
return new_value @staticmethod
def roll_die(weights):
if weights:
return choice(range(len(weights)), p=weights)
else:
return None
This Dirichlet process class could be called stochastic memoization. This idea was first articulated in somewhat abstruse terms by Daniel Roy, et al.
Below are histograms of 10000 samples drawn from samplesdrawn from Dirichlet processes with standard normal base distribution and varying α values.
import pandas as pd base_measure = lambda: norm().rvs()
n_samples = 10000
samples = {}
for alpha in [1, 10, 100, 1000]:
dirichlet_norm = DirichletProcessSample(base_measure=base_measure, alpha=alpha)
samples["Alpha: %s" % alpha] = [dirichlet_norm() for _ in range(n_samples)] _ = pd.DataFrame(samples).hist()
Note that these histograms look very similar to the corresponding plots of sampled distributions above. However, these histograms are plotting points sampled from a distribution sampled from a Dirichlet process while the plots above were showing approximate distributions samples from the Dirichlet process. Of course, as the number of samples from each H grows large, we would expect the histogram to be a very good empirical approximation of H.
In a future post, I will look at how this DirichletProcessSampleclass can be used to draw samples from a hierarchicalDirichlet process.
Notes on the Dirichlet Distribution and Dirichlet Process的更多相关文章
- The Dirichlet Distribution 狄利克雷分布 (PRML 2.2.1)
The Dirichlet Distribution 狄利克雷分布 (PRML 2.2.1) Dirichlet分布可以看做是分布之上的分布.如何理解这句话,我们可以先举个例子:假设我们有一个骰子,其 ...
- [Bayes] Multinomials and Dirichlet distribution
From: https://www.cs.cmu.edu/~scohen/psnlp-lecture6.pdf 不错的PPT,图示很好. 伯努利分布 和 多项式分布 Binomial Distribu ...
- Dirichlet Distribution
Beta分布: 二项式分布(Binomial distribution): 多项式分布: Beta分布: Beta分布是二项式分布的共轭先验(conjugate prior) Dirichlet Di ...
- Study notes for Discrete Probability Distribution
The Basics of Probability Probability measures the amount of uncertainty of an event: a fact whose o ...
- Study notes for Latent Dirichlet Allocation
1. Topic Models Topic models are based upon the idea that documents are mixtures of topics, where a ...
- 转:Simple Introduction to Dirichlet Process
来源:http://hi.baidu.com/vyfrcemnsnbgxyd/item/2f10ecc3fc35597dced4f88b Dirichlet Process(DP)是一个很重要的统计模 ...
- [综] Latent Dirichlet Allocation(LDA)主题模型算法
多项分布 http://szjc.math168.com/book/ebookdetail.aspx?cateid=1&§ionid=983 二项分布和多项分布 http:// ...
- mahout系列----Dirichlet 分布
Dirichlet分布可以看做是分布之上的分布.如何理解这句话,我们可以先举个例子:假设我们有一个骰子,其有六面,分别为{1,2,3,4,5,6}.现在我们做了10000次投掷的实验,得到的实验结果是 ...
- 伯努利分布、二项分布、Beta分布、多项分布和Dirichlet分布与他们之间的关系,以及在LDA中的应用
在看LDA的时候,遇到的数学公式分布有些多,因此在这里总结一下思路. 一.伯努利试验.伯努利过程与伯努利分布 先说一下什么是伯努利试验: 维基百科伯努利试验中: 伯努利试验(Bernoulli tri ...
随机推荐
- java中4中类修饰符访问范围
public:本类中可见,同包中可见,子类中可见,其他包中可见. protected:本类中可见,同包中可见,子类中可见,其他包不可见. 默认:本类中可见,同包中可见,子类不可见,其他包不可见. pr ...
- Oracle中查看无效的对象、约束、触发器和索引
.检查无效的数据库对象: SELECT owner, object_name, object_type,status FROM dba_objects WHERE status = 'INVALID' ...
- 在EF的code frist下写稳健的权限管理系统:数据库模型(二)
先从数据库开始,因为是用EF的code frist,所以所有的设计都在解决项目中进行. 先是数据模型开始 我已经建立了四个模型,user,role,action,actiongroup user里面有 ...
- 4.css度量单位
在 CSS 长度设置中,我们经常需要使用到度量单位,即以什么样的单位设计我们的字 体或边框长度.而在 CSS 中长度单位又分为绝对长度和相对长度. 绝对长度指的是现实世界的度量单位,CSS 支持五种绝 ...
- 《Prism 5.0源码走读》Service Locator Pattern
在Prism Bootstrapper里面取实例的时候使用 ServiceLocator模式,使用的是CommonServiceLocator库 (http://commonservicelocato ...
- Android--获取App应用程序的大小
Android对这种方法进行了封装,我们没有权限去调用这个方法,所以我们只能通过AIDL,然后利用Java的反射机制去调用系统级的方法. 下面上代码:(注释比较详细) /** * 作用:-----获取 ...
- oracle 修改密码,解锁
运行里面输入:sqlplus /nolog登录 connect sys/as sysdba修改密码:alter user sys identified by 密码; --(你的是change_on_i ...
- http压力测试
一.http_load程序非常小,解压后也不到100Khttp_load以并行复用的方式运行,用以测试web服务器的吞吐量与负载.但是它不同于大多数压力测试工具,它可以以一个单一的进程运行,一般不会把 ...
- Go时间戳和日期字符串的相互转换
Go语言中,获取时间戳用time.Now().Unix(),格式化时间用t.Format,解析时间用time.Parse. 看实例代码: package main import ( "fmt ...
- 部署报表和 ReportViewer 控件 rdlc
部署报表和 ReportViewer 控件 您可以将报表和 ReportViewer 控件作为应用程序的一部分自由发布.根据控件类型以及报表是配置为本地处理还是远程处理,部署要求会有很大不同.在同一个 ...