Choosing ‘Classes’

I chose the following topics to be the starting point for the ‘Classes’ section of this blog.

1. Intro to Machine Learning : An overview based on the fundamental text by Hastie, Tibshirani, and Friedman Elements of Statistical Learning
2. Convex Optimization : An overview of the computational methods for convex functions based on the Boyd’s Convex Optimization
3. Design of Experiments : Describe the statistical principles of good experimental design using Mead’s The Design of Experiments with added discussion of Experimental Design in the Data Science sphere.
4. Measure-Theoretical Probability : Description of basic concepts in measure-theoretic probability using the hallmark text Probability and Measure by Patrick Billingsley.

I think this is enough for now (if not too much!). I will have asides on Mathematical Statistics, specifically on major topics like ‘p-values’, ‘the central limit theorem’, and ‘confidence intervals’. I will include discussion of topics close to my research interests as well, whenever I feel like that is necessary.

Someone once told me that programming is best learned via projects. To that end, the first non-class sequence will be dedicated to the engineering side of computational statistics. I’ll start with topics like ‘Setting up a Home Server’ and creating a cloud-based postgresql database in the context of web-hosting. In each case, I will do my best to include supporting code that will be found at my github page .

So let’s begin!