Why Most Optimism Bandit Algorithms Have the Same Regret Analysis: A Simple Unifying Theorem
Preprint
Abstract
Several optimism-based stochastic bandit algorithms -- including UCB, UCB-V, linear UCB, and finite-arm GP-UCB -- achieve logarithmic regret using proofs that, despite superficial differences, follow essentially the same structure. This note isolates the minimal ingredients behind these analyses: a single high-probability concentration condition on the estimators, after which logarithmic regret follows from two short deterministic lemmas describing radius collapse and optimism-forced deviations. The framework yields unified, near-minimal proofs for these classical algorithms and extends naturally to many contemporary bandit variants.Keywords
All Related Versions
This publication has 2 references indexed in Scilit:
- Exploration–exploitation tradeoff using variance estimates in multi-armed banditsTheoretical Computer Science, 2009
- Finite-time Analysis of the Multiarmed Bandit ProblemMachine Learning, 2002