Selecting model complexity in learning problems Conference Paper uri icon

abstract

  • To learn (or generalize) from noisy data, one must resist the temptation to pick a model for the underlying process that overfits the data. Many existing techniques solve this problem at the expense of requiring the evaluation of an absolute, a priori measure of each model's complexity. We present a method that does not. Instead, it uses a natural, relative measure of each model's complexity. This method first creates a pool of 'simple' candidate models using part of the data and then selects from among these by using the rest of the data.

name of conference

  • Proceedings of 32nd IEEE Conference on Decision and Control

published proceedings

  • Proceedings of 32nd IEEE Conference on Decision and Control

author list (cited authors)

  • Buescher, K. L., & Kumar, P. R.

citation count

  • 2

complete list of authors

  • Buescher, KL||Kumar, PR

publication date

  • January 1993