Bounds for Learning from Evolutionary-Related Data in the Realizable Case - Archive ouverte HAL Access content directly
Conference Papers Year : 2016

Bounds for Learning from Evolutionary-Related Data in the Realizable Case

Ondřej Kuželka
  • Function : Author
  • PersonId : 982633
Yuyi Wang
  • Function : Author
  • PersonId : 996959
Jan Ramon

Abstract

This paper deals with the generalization ability of classifiers trained from non-iid evolutionary-related data in which all training and testing examples correspond to leaves of a phylogenetic tree. For the re-alizable case, we prove PAC-type upper and lower bounds based on symmetries and matchings in such trees.
Fichier principal
Vignette du fichier
2016-ijcai-Kuzelka.pdf (207.81 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01422033 , version 1 (23-12-2016)

Identifiers

  • HAL Id : hal-01422033 , version 1

Cite

Ondřej Kuželka, Yuyi Wang, Jan Ramon. Bounds for Learning from Evolutionary-Related Data in the Realizable Case. International Joint Conference on Artificial Intelligence (IJCAI), Jul 2016, New York, United States. ⟨hal-01422033⟩
501 View
68 Download

Share

Gmail Facebook X LinkedIn More