# On the Complexity of Bandit Linear Optimization

11 Aug 2014

We study the attainable regret for online linear optimization problems with bandit feedback, where unlike the full-information setting, the player can only observe its own loss rather than the full loss vector. We show that the price of bandit information in this setting can be as large as $d$, disproving the well-known conjecture that the regret for bandit linear optimization is at most $\sqrt{d}$ times the full-information regret... (read more)

PDF Abstract

# Code Add Remove Mark official

No code implementations yet. Submit your code now