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

Kuzelka, Ondrej; Wang, Yuyi; Ramon, Jan

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

Download BibTeX Cite

Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence. Pages 1655-1660.

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 realizable case, we prove PAC-type upper and lower bounds based on symmetries and matchings in such trees.

Ondrej Kuzelka, Yuyi Wang, and Jan Ramon. 2016. Bounds for Learning from Evolutionary-Related Data in the Realizable Case. In Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-16. IJCAI, 1655–1660. https://ijcai.org/proceedings/2016/237

@inproceedings{ijcai2016p237,
  title     = {Bounds for Learning from Evolutionary-Related Data in the Realizable Case},
  author    = {Kuzelka, Ondrej and Wang, Yuyi and Ramon, Jan},
  booktitle = {Proceedings of the Twenty-Fifth International Joint Conference on
               Artificial Intelligence, {IJCAI-16}},
  publisher = {AAAI Press / International Joint Conferences on Artificial Intelligence},
  editor    = {Subbarao Kambhampati},
  pages     = {1655--1660},
  year      = {2016},
  month     = {7},
  url       = {https://ijcai.org/proceedings/2016/237},
}

TY  - CPAPER
TI  - Bounds for Learning from Evolutionary-Related Data in the Realizable Case
AU  - Kuzelka, Ondrej
AU  - Wang, Yuyi
AU  - Ramon, Jan
T2  - Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-16
PB  - AAAI Press / International Joint Conferences on Artificial Intelligence
PY  - 2016
SP  - 1655
EP  - 1660
UR  - https://ijcai.org/proceedings/2016/237
ER  -