Deep gratitude to Prof. Ed George, who opened a door to the world of emperical bayes for me, I began to read Prof. Jim Berger’s book Statistical Decision Theory and Bayesian Analysis (1985). Here I mainly focus on Chapter 1, 3, 4, 5 of Jim’s book and also share some thoughts on Ed’s paper Minimax Multiple Shrinkage Estimation (1986).

Why Bayesian?

Different people would have different conclusions based on their prior beliefs of the plausibility of the event, Baysian analysis is to seek to utilize prior information.

I attended the SAMSI Agent-based Modeling Workshop in Duke University on March 11-12, 2019. As one of the youngest attendants I would like to share some of the limelights discussed in this workshop.

Description: Agent-based modeling is widely used across many disciplines to study complex emergent behavior generated from simulated entities that interact with each other and their environment according to relatively simple rules. Applications include automobile traffic modeling, weather forecasting, and the study of epidemics. The inferential challenge of agent-based models is that (in general) there is no tractable likelihood function, and thus it is difficult to fit the model or make quantified statements about the accuracy of predictions. This workshop addressed that challenge from the perspective of uncertainty quantification, so that emulator methodology could be used to make approximate principled inferences about agent-based simulations.

The note is partially based on the Bayesian Nonparametrics Machine Learning lectures by Yee Whye Teh at Max Planck Institute for Intelligent Systems in Tübingen, Germany.

Machine learning is all about data, and the uncertainty and complex process in the data. Probability theory is a rich language to express uncertainties. Graphical tool and complex models are develped to help visualize and derive algorithmic solutions.

As we know, Gaussian processes modeling is often refer to as nonparametric modeling. But why? It has parameters in its covariance kernel:
$$\begin{align*} K(x_i,x_j) = h^2\text{exp}\left(\frac{-(x_i-x_j)^2}{\lambda^2}\right) \end{align*}$$
From the example of Gaussian kernel above, $h$ and $\lambda$ are the hyperparameters.

Today is my friend’s BIG DAY! Happy Birthday!!! He is one of the four people who changed my life (yes four people have seminal impact in my life so far). I want to thank him for all the things he has done for me and all the opportunites he gave me. So I decide to make a birthday cake for him.

Here it is!!!

My current blog theme is 日神 x 酒神 (Apollinian and Dionysian).

Apollo: the God of the sun, truth, light, and logic, is the namesake for the first, ordered, half. This is the half that covers everything which is structured.
Dionysus: the God of wine, festivals, and madness lends his name to the later, frenzied, half. The Dionysian doesn’t categorize and tends to blur the boundaries between the self and nature with emotion.

I consent Nietzsche’s idea that we need both in our life to be complete people. The fusion of these two drives allows the tremendous frenzied energy of the Dionysian to be applied constructively inside an Apollonian framework.

When we write articles, we always want to know the popularity of our work. As a Hexo blogger, I tried several different visitor counter system and here, like the previous post, I will summarize two options for visitor counts to each articles. But this time, I have preference to a specific one. Guess which one?

• Option 1: LeanCloud Counter
• Option 2: Firestore Counter

LeanCloud Counter

LeanCloud is a Chinese friendly system, and unfortunately it doesn’t have English version. Here I’ll try to make it as clear as possible. For those who’ve read the previous post, it is not hard for you to find out Valine Comment actually use LeanCloud system so if you already have Valine, you don’t need to create the account again.

Hexo as a static site generator has become a popular choice for bloggers. When using something like WordPress or Medium you get a comment section out of the box sponstaneously, it is not as straightforward in a static environment. In this article, I will summarize two options to provide your audience with a way to leave a comment.

• Option 1: Disqus Comment
• Option 2: Valine Comment

Disque Comment

Disqus Comment is a great way to let people comment on your articles. Disqus has automatic setup for nearly every Content Management System (CMS) except Hexo. Here is the easy way to set this up:

I created my blog with Hexo and in this article I’ll talk about how to create Local Search with hexo-generator-search plugin. I use hexo-theme-next version 5.1.4. (for the previous version localsearch.swig file needs to be modified.)

Install Plugin

First, install hexo-generator-search plugin plugin by the command below:

1

$ npm install hexo-generator-search --save

Then configure this plugin in _config.yml file of your theme.