Stochastic Gradient Descent

with No Comments

Most machine learning algorithms and statistical inference techniques operate on the entire dataset.  Think of ordinary least squares regression or estimating generalized linear models.  The minimization step of these algorithms is either performed in place in the case of OLS … Read More

Destructuring in Mathematica

with 1 Comment

A technique that I have particularly useful in Lisp-like languages like Mathematica and Clojure is destructuring. Destructuring is a mechanism for extracting parts of an expression. The Lisp “code as data” paradigm lends itself to destructuring techniques. I recently leveraged … Read More

Incanter and the GLM

with 2 Comments

I read somewhere that the Generalized Linear Model is the “workhorse of statistics” though I cannot seem to find the reference anymore.  The workhorse of statistics is so called because it unifies regression for the exponential family of probability distributions … Read More

Monte Carlo Pi calc

with 1 Comment

What is the first app that you code up in a new language that you are learning?  I imagine most people start with the canonical “Hello World” and then move on to their own specific app.  A colleague of mine … Read More

1 2