We mentioned this before a year ago, here are the slides: Random forests with random projections of the output space for high dimensional multi-label classification by Arnaud Joly, Pierre Geurts, Louis Wehenkel.
The implementation of the random output tree is here at: https://github.com/arjoly/random-output-trees
Liked this entry ? subscribe to Nuit Blanche's feed, there's more where that came from. You can also subscribe to Nuit Blanche by Email, explore the Big Picture in Compressive Sensing or the Matrix Factorization Jungle and join the conversations on compressive sensing, advanced matrix factorization and calibration issues on Linkedin.