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

Ondřej Kuželka 1 Yuyi Wang 2 Jan Ramon 3
3 MAGNET - Machine Learning in Information Networks
Inria Lille - Nord Europe, CRIStAL - Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189
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.
Complete list of metadatas

Cited literature [14 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01422033
Contributor : Jan Ramon <>
Submitted on : Friday, December 23, 2016 - 2:25:52 PM
Last modification on : Friday, March 22, 2019 - 1:34:37 AM
Long-term archiving on : Tuesday, March 21, 2017 - 7:25:47 AM

File

2016-ijcai-Kuzelka.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01422033, version 1

Citation

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⟩

Share

Metrics

Record views

657

Files downloads

226