On-Line Learning with Delayed Label Feedback

Abstract

We generalize on-line learning to handle delays in receiving labels for instances. After receiving an instance x , the algorithm may need to make predictions on several new instances before the label for x is returned by the environment. We give two simple techniques for converting a traditional on-line algorithm into an algorithm for solving a delayed on-line problem. One technique is for instances generated by an adversary; the other is for instances generated by a distribution. We show how these techniques effect the original on-line mistake bounds by giving upper-bounds and restricted lower-bounds on the number of mistakes.

Cite

Text

Mesterharm. "On-Line Learning with Delayed Label Feedback." International Conference on Algorithmic Learning Theory, 2005. doi:10.1007/11564089_31

Markdown

[Mesterharm. "On-Line Learning with Delayed Label Feedback." International Conference on Algorithmic Learning Theory, 2005.](https://mlanthology.org/alt/2005/mesterharm2005alt-online/) doi:10.1007/11564089_31

BibTeX

@inproceedings{mesterharm2005alt-online,
  title     = {{On-Line Learning with Delayed Label Feedback}},
  author    = {Mesterharm, Chris},
  booktitle = {International Conference on Algorithmic Learning Theory},
  year      = {2005},
  pages     = {399-413},
  doi       = {10.1007/11564089_31},
  url       = {https://mlanthology.org/alt/2005/mesterharm2005alt-online/}
}