Posts

This year, I’ve been trying to read something other than statistics. Thanks to my friend Wenxuan who sent me a book titled A Gentleman in Moscow, I started this journey.

Time passes unbelievably fast and here comes the end of 2022! It has been a year with a lot of personal growth and I want to pay it a tribute with this brief post.

Recently I traveled to Houston and got my first tattoo done. I have been thinking about getting a tattoo for years although it has been long regarded as a sign of rebellion in most eastern cultures.

Today something good happened in my life. I will share more when it is appropriate. Overall I am exhausted, having worked hard for a while…but also really happy. Tiger’s birthday is coming up!

Here is a bucket list, and it will be actively updated (and hopefully also actively checked) in the future. Below I added some updates from 04/04/2022. Travel to at least one country except for US and China in 2020 Because of covid-19, I have not been able to travel internationally yet.

I have always been puzzled and amazed by the idea of “embedding”. A high-dimensional space, such as a corpus for a language, can be represented using, say, only 50 dimensions. How amazing!

This winter I took my very first paid time off (PTO) in my life after starting a job. During a period of 18 days, I have taken a total of 8 flights, both domestic and international.

I have been a Mac user for more than 6 years now, yet occasionally I have been attracted by Linux. Compared with Mac, I like the complete openess of Linux systems and the communications in the Linux user community.

Another important type of data is the time-to-event structured survival data, which I worked on during my entire PhD study. Different from what we usually see, there may be censoring in survival data, which adds one more layer of complication to modeling.

Following my last post on using tensorflow for linear regression, in this post I am going to extend the scope to generalized linear models. >>> import tensorflow as tf >>> import tensorflow_probability as tfp >>> tfd = tfp.