Monthly Archives: February 2009

Prediction markets, monte carlo, and loss functions

There has been some discussion lately about how to evaluate the performance of different prediction markets (like Intrade), and predictors (like Nate Silver) at guessing the winners of elections, or Oscars. Who is making the best predictions? If everyone simply … Continue reading

Posted in Uncategorized | 11 Comments

The Stalin Compiler

Stalin is a questionably named Scheme compiler written by Jeffrey Mark Siskind that can supposedly create binaries as fast or faster than Fortran or C for numerical problems. To test this, I tried creating a simple program to numerically integrate … Continue reading

Posted in Uncategorized | Tagged , , , | 10 Comments

Automatic Differentiation: The most criminally underused tool in the potential machine learning toolbox?

Update: (November 2015) In the almost seven years since writing this, there has been an explosion of great tools for automatic differentiation and a corresponding upsurge in its use. Thus, happily, this post is more or less obsolete. I recently … Continue reading

Posted in Uncategorized | 47 Comments