This article introduces the concepts around Online Bandit Linear Optimization and explores an efficient setup called SCRiBLe (Self-Concordant Regularization in Bandit Learning) created by Abernethy et. al.\cite{abernethy}. The SCRiBLe setup and algorithm yield a O(T) regret bound and polynomial run time complexity bound on the dimension of the input space. In this article we build up to the bandit linear optimization case and study SCRiBLe.
@article{arxiv.1805.05773,
title = {Online Bandit Linear Optimization: A Study},
author = {Vikram Mullachery and Samarth Tiwari},
journal= {arXiv preprint arXiv:1805.05773},
year = {2018}
}