Forest Guided Smoothing

03/08/2021
by   Isabella Verdinelli, et al.
9

We use the output of a random forest to define a family of local smoothers with spatially adaptive bandwidth matrices. The smoother inherits the flexibility of the original forest but, since it is a simple, linear smoother, it is very interpretable and it can be used for tasks that would be intractable for the original forest. This includes bias correction, confidence intervals, assessing variable importance and methods for exploring the structure of the forest. We illustrate the method on some synthetic examples and on data related to Covid-19.

READ FULL TEXT
research
12/11/2021

Confidence intervals for the random forest generalization error

We show that underneath the training process of a random forest there li...
research
03/21/2018

Boosting Random Forests to Reduce Bias; One-Step Boosted Forest and its Variance Estimate

In this paper we propose using the principle of boosting to reduce the b...
research
03/16/2020

A Numerical Transform of Random Forest Regressors corrects Systematically-Biased Predictions

Over the past decade, random forest models have become widely used as a ...
research
02/24/2021

Generalised Boosted Forests

This paper extends recent work on boosting random forests to model non-G...
research
11/30/2021

Modelling hetegeneous treatment effects by quantitle local polynomial decision tree and forest

To further develop the statistical inference problem for heterogeneous t...
research
08/03/2021

Desk Organization: Effect of Multimodal Inputs on Spatial Relational Learning

For robots to operate in a three dimensional world and interact with hum...
research
02/06/2012

rFerns: An Implementation of the Random Ferns Method for General-Purpose Machine Learning

In this paper I present an extended implementation of the Random ferns a...

Please sign up or login with your details

Forgot password? Click here to reset