Gradient Boosting

What is Gradient Boosting?

Gradient boosting is a machine learning technique for regression and classification problems that produce a prediction model in the form of an ensemble of weak prediction models. This technique builds a model in a stage-wise fashion and generalizes the model by allowing optimization of an arbitrary differentiable loss function. Gradient boosting basically combines weak learners into a single strong learner in an iterative fashion. As each weak learner is added, a new model is fitted to provide a more accurate estimate of the response variable. The new weak learners are maximally correlated with the negative gradient of the loss function, associated with the whole ensemble. The idea of gradient boosting is that you can combine a group of relatively weak prediction models to build a stronger prediction model. 

Why is this Useful?

It is a very powerful technique for building predictive models. Gradient boosting is applicable to many different risk functions and optimizes prediction accuracy of those functions, which is an advantage to conventional fitting methods. This allows for freedom in model design. It also addresses concerns about multicollinearity problems, which is a problem where there is high correlations between two or more predictor variables. Gradient boosting models have shown success in practical applications, and in various machine learning and data mining challenges.

Practical Uses of Gradient Boosting

  • Neurobotics – Gradient boosting is a useful practical tool for predictive tasks, and consistently provides higher accuracy results compared to conventional single strong machine learning models. For example, gradient boosting helps to create models that can map the EMG and EEG sensor readings to human movement tracking and activity recognition.