The search functionality is under construction.
The search functionality is under construction.

Asymptotic Evaluation of Classification in the Presence of Label Noise

Goki YASUDA, Tota SUKO, Manabu KOBAYASHI, Toshiyasu MATSUSHIMA

  • Full Text Views

    0

  • Cite this

Summary :

In a practical classification problem, there are cases where incorrect labels are included in training data due to label noise. We introduce a classification method in the presence of label noise that idealizes a classification method based on the expectation-maximization (EM) algorithm, and evaluate its performance theoretically. Its performance is asymptotically evaluated by assessing the risk function defined as the Kullback-Leibler divergence between predictive distribution and true distribution. The result of this performance evaluation enables a theoretical evaluation of the most successful performance that the EM-based classification method may achieve.

Publication
IEICE TRANSACTIONS on Fundamentals Vol.E106-A No.3 pp.422-430
Publication Date
2023/03/01
Publicized
2022/08/26
Online ISSN
1745-1337
DOI
10.1587/transfun.2022TAP0013
Type of Manuscript
Special Section PAPER (Special Section on Information Theory and Its Applications)
Category
Learning

Authors

Goki YASUDA
  Waseda University
Tota SUKO
  Waseda University
Manabu KOBAYASHI
  Waseda University
Toshiyasu MATSUSHIMA
  Waseda University

Keyword