Learning from Networked Examples - Archive ouverte HAL Access content directly
Conference Papers Year : 2017

Learning from Networked Examples

(1) , (2) , (3)
1
2
3
Yuyi Wang
  • Function : Author
  • PersonId : 996959
Jan Ramon

Abstract

Many machine learning algorithms are based on the assumption that training examples are drawn independently. However, this assumption does not hold anymore when learning from a networked sample because two or more training examples may share some common objects, and hence share the features of these shared objects. We show that the classic approach of ignoring this problem potentially can have a harmful effect on the accuracy of statistics, and then consider alternatives. One of these is to only use independent examples, discarding other information. However, this is clearly suboptimal. We analyze sample error bounds in this networked setting, providing significantly improved results. An important component of our approach is formed by efficient sample weighting schemes, which leads to novel concentration inequalities.
Fichier principal
Vignette du fichier
wang17a.pdf (347.32 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-02519274 , version 1 (25-03-2020)

Identifiers

  • HAL Id : hal-02519274 , version 1

Cite

Yuyi Wang, Zheng-Chu Guo, Jan Ramon. Learning from Networked Examples. ALT 2017 - 28th conference on Algorithmic Learning Theory, Oct 2017, Kyoto, Japan. pp.1 - 26. ⟨hal-02519274⟩
47 View
42 Download

Share

Gmail Facebook Twitter LinkedIn More