From Batch to Transductive Online Learning

Abstract

It is well-known that everything that is learnable in the difficult online setting, where an arbitrary sequences of examples must be labeled one at a time, is also learnable in the batch setting, where examples are drawn independently from a distribution. We show a result in the opposite di- rection. We give an efficient conversion algorithm from batch to online that is transductive: it uses future unlabeled data. This demonstrates the equivalence between what is properly and efficiently learnable in a batch model and a transductive online model.

Cite

Text

Kakade and Kalai. "From Batch to Transductive Online Learning." Neural Information Processing Systems, 2005.

Markdown

[Kakade and Kalai. "From Batch to Transductive Online Learning." Neural Information Processing Systems, 2005.](https://mlanthology.org/neurips/2005/kakade2005neurips-batch/)

BibTeX

@inproceedings{kakade2005neurips-batch,
  title     = {{From Batch to Transductive Online Learning}},
  author    = {Kakade, Sham and Kalai, Adam Tauman},
  booktitle = {Neural Information Processing Systems},
  year      = {2005},
  pages     = {611-618},
  url       = {https://mlanthology.org/neurips/2005/kakade2005neurips-batch/}
}