Online Learning with Noisy Side Observations

@inproceedings{Kock2016OnlineLW,
  title={Online Learning with Noisy Side Observations},
  author={Tom{\'a}s Koc{\'a}k and Gergely Neu and Michal Valko},
  booktitle={AISTATS},
  year={2016}
}
We propose a new partial-observability model for online learning problems where the learner, besides its own loss, also observes some noisy feedback about the other actions, depending on the underlying structure of the problem. We represent this structure by a weighted directed graph, where the edge weights are related to the quality of the feedback shared by the connected nodes. Our main contribution is an efficient algorithm that guarantees a regret of Õ( √ α∗T ) after T rounds, where α∗ is a… CONTINUE READING

References

Publications referenced by this paper.
Showing 1-10 of 16 references

Efficient learning by implicit excitedon in bandit problems with side observations

  • Kocák, Tomáš, +5 authors Rémi
  • In Neural Information Processing Systems,
  • 2014
Highly Influential
14 Excerpts

If a, b ≥ 0 and a+ b ≥ B > A > 0, then a a+ b−A

  • Alon
  • 2013

Kocák et al. (2014), we use following two lemmas to bound Qt

  • Alon
  • Lemma 3. (cf. Lemma 10 of Alon et al
  • 2013

Similar Papers

Loading similar papers…