Asymptotic statistical theory of overtraining and cross-validation

Shun Ichi Amari, Noboru Murata, Klaus Robert Müller, Michael Finke, Howard Hua Yang

研究成果: Article査読

247 被引用数 (Scopus)


A statistical theory for overtraining is proposed. The analysis treats general realizable stochastic neural networks, trained with Kullback-Leibler divergence in the asymptotic case of a large number of training examples. It is shown that the asymptotic gain in the generalization error is small if we perform early stopping, even if we have access to the optimal stopping time. Considering cross-validation stopping we answer the question: In what ratio the examples should be divided into training and cross-validation sets in order to obtain the optimum performance. Although cross-validated early stopping is useless in the asymptotic region, it surely decreases the generalization error in the nonasymptotic region. Our large scale simulations done on a CM5 are in nice agreement with our analytical findings.

ジャーナルIEEE Transactions on Neural Networks
出版ステータスPublished - 1997

ASJC Scopus subject areas

  • Software
  • Computer Science Applications
  • Computer Networks and Communications
  • Artificial Intelligence

フィンガープリント 「Asymptotic statistical theory of overtraining and cross-validation」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。