Horace Guy's blog about random things
Live Last read · last published · next check
Monthly Payments: loan & interest As a young-ish professional, I’ve been wondering whether I should buy my primary residence or keep renting. With this thought, I’ve been driven to answer this question in a rational manner. You can see the results of this investigation on this website: linemo . Loan interest rates It all started when I wanted to know how much I would pay in interest for a loan.…
Prior, posterior and likelihood Reuse CC BY 4.0 Citation BibTeX citation: @online{guy2025, author = {Guy, Horace}, title = {An Interactive Introduction to Probabilistic Programming}, date = {2025-01-06}, url = {https://blog.horaceg.xyz/posts/intro-ppl/}, langid = {en} } For attribution, please cite this work as: Guy, Horace. 2025. “An Interactive Introduction to Probabilistic Programming.” January…
I first learned about bayesian statistics in a job posting for an internship. At the time, I was about 20 years old and had never heard of it. The concept was so alien to me that I first read bayesian interference . I figured it had something to do with optics, such as the Michelson interferometer that I (still) fear. Fast-forward a small decade and I now consider myself a (secular) bayesian. What…
Disclaimer: this post is heavily based on Introduction to variational auto-encoders, Kingma & Welling, 2019 [^intro-vae] Introduction As of April 2024, the VAE Paper from 2013 has been cited more than 34 thousand times. What can we learn from the variational auto-encoder ? The framework of VAE provides a principled method for jointly learning deep latent-variable models and corresponding inference…
TL; DR: My own code is on github . An attempt at crafting interpreters Due to the warm reviews, I tried first to read Crafting Interpreters and went though the first chapters, but I was quickly underwhelmed. Indeed I found the following: The language of the first part is Java, which I am not proficient in. I still managed to roughly translate the scanning part to python, but I am not familiar with…
Lately I’ve been interested in probabilistic programming languages (PPL). I was wondering what would a PPL from the future look like ? State of the art Probabilistic programming In a nutshell, probabilistic programming is about making computer reason about statistical bayesian inference. It refers to a domain-specific language, embedded in a host language or not, where the user declares a model of…
I decided to do my resume since I haven’t done it in a while. My old one was based on the latex template moderncv . But this time, I wanted to have one for the web that looks good on desktop and mobile, as well as paper (pdf). TL;DR: resume.horaceg.xyz The header of my resume Inspiration I saw a blog post by Christophe-Marie Duquesne that seemed to exactly fit the bill. It is even inspired by…
A machine (server) handling multiple requests at once, illustrating concurrency. Include the Python logo prominently. Made with ChatGPT I’ve struggled for a long time with concurrency and parallelism. Let’s dive in with the hot-cool-new ASGI framework, FastAPI . It is a concurrent framework, which means asyncio -friendly. Tiangolo, the author, claims that the performance is on par with Go and Node…
A diagram of the overall workflow In March 2020, lockdown measures were implemented all over the world due to the spread of Covid-19. I was at home, a bit bored and I was looking for something to do. TL;DR : - Kaggle submission - Github repo Mobility datasets Google and Apple published datasets related to (anonymized) activity of smartphones users. They called this mobility data, although this…
Tinkerer imagining great things while looking at a computer screen. Made with ChatGPT As a data scientist by day, and tinkerer by night, I am often browsing Hacker News and the like in order to be up-to-date with the latest cool technologies. Python On the scientific computing side, there is one behemoth: Python. However, it still isn’t on par with R for statistics. Pandas is often criticized and…
I’ve been wanting to publish online for some time. I was very young during the Wordpress wave, so I was never really drawn into it. Jekyll I learned early about static website, first with Jekyll and Github pages , in 2016. At the time, I was using Windows 10 and wasn’t quite experienced. Since Jekyll is written 1 in Ruby, I needed to bootstrap Ruby and the many gems required to run the blog. It…
(sports) Betting is similar to gambling Introduction Have you ever placed a bet ? Wondered what the odds actually mean ? It’s all linked to probability. Setup Let us place focus on a betting situation: a bookie offers odds on an event , and on its complementary . There can be multiple binary events at the same time (or close). We will then extend to multiple outcomes. In our case, we consider…
Lately, I have been interested in the foundations of machine learning (ML) in a pedagogical perspective. A first step to grasp the power of ML is gradient descent. So, I was determined to demonstrate the way it works with an interactive app. Python and Jupyter world The first thing I made used Jupyter , and a nifty package called Voilà , that turns a notebook into a standalone app. For automatic…
