Luciano Floridi poses the problem of second-order probabilities:

(…) we actually lack a theory of second order probability, let alone a philosophical justification for it.

By second order, he means “probabilities about probabilisties”.

I beg to differ with Luciano. What about this reference?

Gaifman, H. 1986. A theory of higher order probabilities. In Proceedings of the 1986 Conference on theoretical Aspects of Reasoning About Knowledge

I learned on Ted Serbinski that Scott Reynolds, who implements the Slope One Collaborative Filtering algorithm in Drupal, is being paid by Google. It is one of 14 projects that Google decided to fund. Way to go Google!

Click on the picture to see it all. Don’t ask me what Louka ate, I have no idea. You can see Lohan is quite aware of the camera. My wife is enjoying a good book.

Update: According to my wife, Louka was eating sand. Gross!

Olivier Bousquet questions Statistical Learning Theory.

So, I think that the theoretical analysis is mainly a way to popularize an algorithm and to raise its visibility. The effect is then that more people try it out, and streamline it. So in the end, the algorithm may be adopted, but a theoretical analysis rarely justifies the algorithm and never provides guarantees. Hence theory is a way to attract attention to an algorithm. It should also be a way to get new insights for the development of new algorithms, but this happens much less frequently than is claimed!

I’m currently working on a paper where I spent a lot of time fiddling and proving some bounds, as Olivier points out we often do. Of course, not being a pure theory guy, I also run extensive experiments. I cannot help but notice a strong disconnect between the theory and the practice, not only in what I do, but in the papers I cite.

The counter-argument might be: but theory helps design better algorithms. Like Olivier, I don’t buy it.

Ah! I still do theory of course, but let’s not fool ourselves in thinking we are smarter than nature.

Scott Reynolds has been working hard to implement Slope One collaborative filtering in Drupal. You can see his latest code in viewcvs.