In this post, I will discuss a paper published by Arora et al. in 2015, titled RAND-WALK: A Latent Variable Model Approach to Word Embeddings. This paper is interesting because the authors provide a generative model that explains the success of word embedding algorithms that are popular in practice: pointwise mutual information (PMI), word2vec, and GloVe.

I’m still quite a novice cook, so I think the best way to get better at it is to repeatedly cook the same dish over and over again. The first dish I’m trying this summer is paella, a popular Spanish dish.

In this blog post, I will explore an application of probability in the realm of approximation algorithms. The material here is from Chapter 3 of in Roman Vershynin’s textbook on High Dimensional Probability.

On this site, I previously had an NBA analytics tutorial. I have since converted my GitHub page into a blog :) I spent some time today trying to convert the Jupyter Notebook to markdown and posting it onto here, but I was running into some annoying format issues. So I gave up (for now). You can still access the notebook here.