Warm-starting Contextual Bandits: Robustly Combining Supervised and Bandit Feedback

Understand

We investigate the feasibility of learning from a mix of both fully-labeled supervised data and contextual bandit data.

• We specifically consider settings in which the underlying learning signal may be different between these two data sources.
• Theoretically, we state and prove no-regret algorithms for learning that is robust to misaligned cost distributions between the two sources.
• Empirically, we evaluate some of these algorithms on a large selection of datasets, showing that our approach is both feasible and helpful in practice.