Functional Models for Regression Tree Leaves

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Local Linear Forests (2018, methodology): “The main draw of this results is that the best attainable rate of convergence βmin is improved compared to the rate βrf from (15) obtained in Wager and Athey [2018]. The reason we were able to obtain such an improvement in the rate of convergence is that we have assumed and consequently exploited sm”
Learning model trees from evolving data streams (2010, methodology): “In one category are falling algorithms like M5 (Quinlan 1992), CART (Breiman et al. 1998), HTL ( Torgo 1997 ).”
Bayesian Treed Models (2002, methodology): “Torgo (1997) uses linear models, k-nearest neighbors, or kernel regressors in terminal nodes, but also adds these to a conventional tree after growing.”
Fifty Years of Classification and Regression Trees (2014, methodology): “Torgo (1997) took a similar approach, but allowed kernel regression and nearest-neighbor models in addition to linear models in the terminal nodes.”
Functional Trees (2001, background): “Torgo (1997) has presented an experimental study about functional models for regression tree leaves.”
Bayesian Treed Generalized Linear Models (2003, unknown): “This approach is taken by Quinlan (1992) and Torgo (1997).”