Practical Contextual Bandits with Feedback Graphs
This work addresses the challenge of reducing statistical complexity in contextual bandits for real-world applications, though it appears incremental as it builds on existing feedback graph frameworks.
The paper tackles the problem of improving learning efficiency in contextual bandits by leveraging feedback graphs, and it proposes a reduction-to-regression approach that achieves minimax rates while being computationally practical.
While contextual bandit has a mature theory, effectively leveraging different feedback patterns to enhance the pace of learning remains unclear. Bandits with feedback graphs, which interpolates between the full information and bandit regimes, provides a promising framework to mitigate the statistical complexity of learning. In this paper, we propose and analyze an approach to contextual bandits with feedback graphs based upon reduction to regression. The resulting algorithms are computationally practical and achieve established minimax rates, thereby reducing the statistical complexity in real-world applications.