On the Role of Update Constraints and Text-Types in Iterative Learning

Abstract

The present work investigates the relationship of iterative learning with other learning criteria such as decisiveness, caution, reliability, non-U-shapedness, monotonicity, strong monotonicity and conservativeness. Building on the result of Case and Moelius that iterative learners can be made non-U-shaped, we show that they also can be made cautious and decisive. Furthermore, we obtain various special results with respect to one-one texts, fat texts and one-one hypothesis spaces.

Cite

Text

Jain et al. "On the Role of Update Constraints and Text-Types in Iterative Learning." International Conference on Algorithmic Learning Theory, 2014. doi:10.1007/978-3-319-11662-4_5

Markdown

[Jain et al. "On the Role of Update Constraints and Text-Types in Iterative Learning." International Conference on Algorithmic Learning Theory, 2014.](https://mlanthology.org/alt/2014/jain2014alt-role/) doi:10.1007/978-3-319-11662-4_5

BibTeX

@inproceedings{jain2014alt-role,
  title     = {{On the Role of Update Constraints and Text-Types in Iterative Learning}},
  author    = {Jain, Sanjay and Kötzing, Timo and Ma, Junqi and Stephan, Frank},
  booktitle = {International Conference on Algorithmic Learning Theory},
  year      = {2014},
  pages     = {55-69},
  doi       = {10.1007/978-3-319-11662-4_5},
  url       = {https://mlanthology.org/alt/2014/jain2014alt-role/}
}