On reducing the order of arm-passes bandit streaming algorithms under memory bottleneck

Santanu Rathod

On reducing the order of arm-passes bandit streaming algorithms under memory bottleneck

Machine Learning 2021-12-14 v1

Authors: Santanu Rathod

Abstract

In this work we explore multi-arm bandit streaming model, especially in cases where the model faces resource bottleneck. We build over existing algorithms conditioned by limited arm memory at any instance of time. Specifically, we improve the amount of streaming passes it takes for a bandit algorithm to incur a $O(\sqrt{T\log(T)})$ regret by a logarithmic factor, and also provide 2-pass algorithms with some initial conditions to incur a similar order of regret.

Keywords

multi-arm bandit streaming model memory bottleneck regret bound streaming passes

Cite

@article{arxiv.2112.06130,
  title  = {On reducing the order of arm-passes bandit streaming algorithms under memory bottleneck},
  author = {Santanu Rathod},
  journal= {arXiv preprint arXiv:2112.06130},
  year   = {2021}
}

Comments

15 pages, 2 figures. arXiv admin note: text overlap with arXiv:1901.08387 by other authors without attribution

Related papers

View all related →