On the Complexity of Bandit Linear Optimization
This resolves a fundamental conjecture in bandit learning, revealing significant differences from full-information settings, which is important for researchers in online optimization and machine learning theory.
The paper tackled the problem of online linear optimization with bandit feedback, showing that the regret can be as large as d, disproving a conjecture that it is at most sqrt(d) times the full-information regret.
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. Surprisingly, this is shown using "trivial" modifications of standard domains, which have no effect in the full-information setting. This and other results we present highlight some interesting differences between full-information and bandit learning, which were not considered in previous literature.