You are here

A Divide and Conquer Approach to Learning from Prior Knowledge

TitleA Divide and Conquer Approach to Learning from Prior Knowledge
Publication TypeConference Paper
Year of Publication2000
AuthorsChown, E., and T. G. Dietterich
Conference NameProceedings of the Seventeenth International Conference on Machine Learning
Date Published07/2000
PublisherMorgan Kaufmann Publishers Inc.
Conference LocationSan Francisco, CA
ISBN Number1-55860-707-2

This paper introduces a new machine learning task---model calibration---and presents a method for solving a particularly difficult model calibration task that arose as part of a global climate change research project. The model calibration task is the problem of training the free parameters of a scientific model in order to optimize the accuracy of the model for making future predictions. It is a form of supervised learning from examples in the presence of prior knowledge. An obvious approach to solving calibration problems is to formulate them as global optimization problems in which the goal is to find values for the free parameters that minimize the error of the model on training data. Unfortunately, this global optimization approach becomes computationally infeasible when the model is highly nonlinear. This paper presents a new divide-and-conquer method that analyzes the model to identify a series of smaller optimization problems whose sequential solution solves the global calibrat...